Image-Text-to-Text
Transformers
Safetensors
lfm3_vl
liquid
lfm3
edge
conversational
custom_code
Eval Results
Instructions to use LiquidAI/LFM3-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiquidAI/LFM3-VL-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="LiquidAI/LFM3-VL-2B", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("LiquidAI/LFM3-VL-2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use LiquidAI/LFM3-VL-2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LiquidAI/LFM3-VL-2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiquidAI/LFM3-VL-2B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/LiquidAI/LFM3-VL-2B
- SGLang
How to use LiquidAI/LFM3-VL-2B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "LiquidAI/LFM3-VL-2B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiquidAI/LFM3-VL-2B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "LiquidAI/LFM3-VL-2B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiquidAI/LFM3-VL-2B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use LiquidAI/LFM3-VL-2B with Docker Model Runner:
docker model run hf.co/LiquidAI/LFM3-VL-2B
|
Download README.md from LiquidAI/LFM3-VL-2B: direct link, hf CLI and curl.
- Browser
- Download file 142 kB
-
https://huggingface.co/LiquidAI/LFM3-VL-2B/resolve/main/README.md
- Command line
-
hf download hf://LiquidAI/LFM3-VL-2B/README.md
-
curl -L -o README.md https://huggingface.co/LiquidAI/LFM3-VL-2B/resolve/main/README.md
142 kB
| library_name: transformers | |
| license: other | |
| license_name: lfm1.0 | |
| license_link: LICENSE | |
| pipeline_tag: image-text-to-text | |
| tags: | |
| - liquid | |
| - lfm3 | |
| - edge | |
| - conversational | |
| - custom_code | |
| language: | |
| - en | |
| - ar | |
| - zh | |
| - fr | |
| - de | |
| - it | |
| - ja | |
| - ko | |
| - pt | |
| - es | |
| - vi | |
| - th | |
| - id | |
| - hi | |
| - ru | |
| - pl | |
| base_model: LiquidAI/LFM3-1.7B-Base | |
| <div align="center"> | |
| <img | |
| src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/liquid-ai-banner.webp" | |
| alt="Liquid AI" | |
| style="width: 100%; max-width: 100%; height: auto; display: block; margin: 0;" | |
| /> | |
| <div align="center" style="display: flex; justify-content: center; align-items: center; gap: 1.25em; margin: 8px 0 1.7rem; padding: 0; line-height: 1.3;"> | |
| <a href="https://console.liquid.ai/dashboard" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/api.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>API</strong></a> | |
| <a href="https://playground.liquid.ai/" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/try.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Try</strong></a> | |
| <a href="https://docs.liquid.ai/lfm/getting-started/welcome" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/docs.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Docs</strong></a> | |
| <a href="https://www.liquid.ai/blog/lfm3" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/blog.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Blog</strong></a> | |
| </div> | |
| </div> | |
| # LFM3-VL-2B | |
| LFM3-VL-2B is a **vision-language model for on-device visual understanding**. It takes text, images, and video as input, and combines the [LFM3 language model](https://huggingface.co/LiquidAI/LFM3-1.7B-Base) with a new in-house vision encoder. | |
| New in LFM3-VL-2B: | |
| - **Video understanding:** the first LFM vision model that takes video as input. Ask questions about a recorded lecture, a walkthrough filmed on your phone, or a clip from a camera feed. | |
| - **Thinking:** the model reasons step by step before it answers. This helps most with harder visual questions, such as math, charts, and multi-step problems. | |
| - **Spatial and embodied reasoning:** the model finds objects and reasons about how they are placed relative to each other, a strong foundation for robotics applications. | |
| Find more information about the LFM3 family in [our release blog post](https://www.liquid.ai/blog/lfm3). | |
| ## Model details | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| The [LFM3 family](https://huggingface.co/collections/LiquidAI/lfm3) includes base, text, vision, audio, omni, and decision models. | |
| <table style="width: 100%; display: table; border: 0; border-radius: 0; border-collapse: collapse;"> | |
| <thead style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Property</th> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Specification</th> | |
| </tr> | |
| </thead> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Checkpoint</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Post-trained vision-language model</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Parameters</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">1.92B: 1.73B language model, 164M vision encoder, 25M projector</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Language model</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">LFM3, 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Vision encoder</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">14 layers: 8 gated depthwise 2D convolutions, 6 bidirectional attention, 16×16 patches with 2D rotary embeddings</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Inputs</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Text, images, and video at native resolution. Each 2×2 block of patches becomes one language token. Video is sampled at 2 fps.</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Context length</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">128K tokens (input + output)</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Vocabulary</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">128,000 tokens</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>Languages</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>License</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="LICENSE">LFM Open License v1.0</a></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| LFM3-VL-2B is designed for on-device visual tasks: questions about video, reading documents, charts, and app screens, finding objects in an image, and spatial reasoning for robots. It is not recommended for coding, multi-turn conversations, or complex reasoning. | |
| ## Inference | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| Choose a checkpoint variant for your inference framework and hardware. | |
| <table style="width: 100%; display: table; border: 0; border-radius: 0; border-collapse: collapse;"> | |
| <thead style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Checkpoint</th> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Framework</th> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Description</th> | |
| </tr> | |
| </thead> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B">BF16</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/gpu-inference/vllm">vLLM</a>, <a href="https://docs.liquid.ai/deployment/gpu-inference/sglang">SGLang</a>, <a href="https://docs.liquid.ai/deployment/gpu-inference/transformers">Transformers</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">BF16 weights for GPU inference.</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF">GGUF</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/on-device/llama-cpp">llama.cpp</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Local inference on CPUs and GPUs.</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B-MLX-4bit">MLX</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/on-device/mlx">MLX-VLM</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">4-bit quantization for Apple Silicon.</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://huggingface.co/LiquidAI/LFM3-VL-2B-ONNX">ONNX</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><a href="https://docs.liquid.ai/deployment/on-device/onnx">ONNX Runtime</a></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Cross-platform inference with ONNX Runtime.</td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| **Sampling parameters:** `temperature=0.1, top_p=1.0, top_k=50, min_p=0.0, repetition_penalty=1.1`. For image and video preprocessing, use the values in `processor_config.json`. | |
| **Transformers quick start** (`transformers>=5.21.0`): | |
| ```bash | |
| pip install "transformers>=5.21.0" torch torchvision pillow | |
| ``` | |
| ```python | |
| import torch | |
| from transformers import AutoModelForImageTextToText, AutoProcessor | |
| model_id = "LiquidAI/LFM3-VL-2B" | |
| model = AutoModelForImageTextToText.from_pretrained( | |
| model_id, dtype=torch.bfloat16, device_map="auto", trust_remote_code=True | |
| ) | |
| processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True) | |
| messages = [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "image", "url": "https://placecats.com/300/200"}, | |
| {"type": "text", "text": "Describe this image."}, | |
| ], | |
| } | |
| ] | |
| inputs = processor.apply_chat_template( | |
| messages, | |
| add_generation_prompt=True, | |
| tokenize=True, | |
| return_dict=True, | |
| return_tensors="pt", | |
| ).to(model.device) | |
| with torch.inference_mode(): | |
| output_ids = model.generate( | |
| **inputs, | |
| do_sample=True, | |
| temperature=0.1, | |
| top_k=50, | |
| repetition_penalty=1.1, | |
| max_new_tokens=16384, # generate() needs an explicit limit; reasoning can be long | |
| ) | |
| generated_ids = output_ids[:, inputs["input_ids"].shape[1] :] | |
| print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0]) | |
| ``` | |
| <details> | |
| <summary><strong>On-device inference with llama.cpp</strong></summary> | |
| For most on-device use cases, we recommend [llama.cpp](https://github.com/ggml-org/llama.cpp) b11960 or newer with the [GGUF checkpoints](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF). The fastest way to try it is [Llama.app](https://llama.app) for macOS and Windows: on the [GGUF page](https://huggingface.co/LiquidAI/LFM3-VL-2B-GGUF), click **Use this model → llama**. | |
| From a terminal, start a web chat UI and an OpenAI-compatible API at `http://localhost:8080`. With `-hf`, llama.cpp downloads the model and the matching vision projector (mmproj): | |
| ```bash | |
| llama serve -hf LiquidAI/LFM3-VL-2B-GGUF:Q4_0 \ | |
| --temp 0.1 --top-p 1.0 --top-k 50 --min-p 0.0 --repeat-penalty 1.1 \ | |
| --no-reasoning-preserve --port 8080 | |
| ``` | |
| To ask one question from the command line, use `llama cli` with the same flags, `--image <IMAGE PATH>` or `--video <VIDEO PATH>`, and `-p "<PROMPT>"`. Video input needs `ffmpeg` in `PATH`. | |
| </details> | |
| <details> | |
| <summary><strong>GPU inference with vLLM and SGLang</strong></summary> | |
| For high-throughput serving on GPU, use [vLLM](https://github.com/vllm-project/vllm) or [SGLang](https://github.com/sgl-project/sglang). Both serve an OpenAI-compatible API. Support for LFM3-VL in SGLang is in review in [sgl-project/sglang#46858](https://github.com/sgl-project/sglang/pull/46858), and support in vLLM is in progress. We will update this card when their releases support it. | |
| **vLLM**: | |
| ```bash | |
| vllm serve LiquidAI/LFM3-VL-2B \ | |
| --reasoning-parser qwen3 \ | |
| --enable-auto-tool-choice --tool-call-parser qwen3_coder \ | |
| --chat-template-content-format openai \ | |
| --structured-outputs-config '{"backend": "xgrammar", "disable_any_whitespace": true}' \ | |
| --media-io-kwargs '{"video": {"video_backend": "qwen3_vl"}}' | |
| ``` | |
| **SGLang**: | |
| ```bash | |
| sglang serve --model-path LiquidAI/LFM3-VL-2B --trust-remote-code \ | |
| --reasoning-parser auto \ | |
| --tool-call-parser auto \ | |
| --constrained-json-disable-any-whitespace | |
| ``` | |
| Send an image-and-text request with the OpenAI client. Change `base_url` to `http://localhost:30000/v1` for SGLang, or `http://localhost:8080/v1` for llama.cpp: | |
| ```python | |
| from openai import OpenAI | |
| client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") | |
| response = client.chat.completions.create( | |
| model="LiquidAI/LFM3-VL-2B", | |
| messages=[ | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "image_url", "image_url": {"url": "https://placecats.com/300/200"}}, | |
| {"type": "text", "text": "Describe this image."}, | |
| ], | |
| } | |
| ], | |
| temperature=0.1, | |
| extra_body={"top_k": 50, "repetition_penalty": 1.1}, | |
| ) | |
| print(response.choices[0].message.content) | |
| ``` | |
| </details> | |
| <details> | |
| <summary><strong>Chat template</strong></summary> | |
| LFM3-VL uses this ChatML format, generated from the checkpoint's [chat template](https://huggingface.co/LiquidAI/LFM3-VL-2B/blob/main/chat_template.jinja): | |
| ```text | |
| <|startoftext|><|im_start|>system | |
| You are a helpful assistant trained by Liquid AI.<|im_end|> | |
| <|im_start|>user | |
| <|vision_start|><|image|><|vision_end|>What species is in this picture?<|im_end|> | |
| <|im_start|>assistant | |
| <think> | |
| ``` | |
| Use `processor.apply_chat_template()` with `add_generation_prompt=True` to format messages automatically. The model thinks in a `<think>...</think>` block before it answers. | |
| The template inserts `<|vision_start|><|image|><|vision_end|>` for each image and `<|vision_start|><|video|><|vision_end|>` for each video. Do not put these tags in your message content. | |
| Reasoning from turns before the latest user message is removed unless `preserve_thinking=True`. | |
| </details> | |
| <details> | |
| <summary><strong>Tool calling</strong></summary> | |
| Pass function schemas through `tools=...` to `apply_chat_template()`. The template formats tool definitions and results automatically. Generated calls use XML: | |
| ```text | |
| <tool_call> | |
| <function=get_weather> | |
| <parameter=city> | |
| Paris | |
| </parameter> | |
| </function> | |
| </tool_call> | |
| ``` | |
| > [!WARNING] | |
| > LFM3's tool call format has changed from the custom LFM2/LFM2.5 format to a superset of `qwen3_coder`. | |
| Execute the call in your application. Add the parsed assistant call to history as a `tool_calls` entry, then append the result as a `tool` message. Keep passing the tool schemas on subsequent requests and preserve the assistant's content and reasoning from the current tool-use turn. | |
| `function.arguments` must be a Python mapping. Decode JSON strings with `json.loads()` before applying the template. | |
| See the [Tool Use documentation](https://docs.liquid.ai/lfm/key-concepts/tool-use) for the full guide. | |
| </details> | |
| <details> | |
| <summary><strong>Tool search</strong></summary> | |
| LFM3 supports deferred tools. Set `defer_loading=True` to keep tool definitions out of the prompt until your harness's search tool returns their names as `tool_reference` parts. The chat template then inserts their definitions into `<additional_tools>`. | |
| ```python | |
| tools = [ | |
| search_tool, | |
| {"type": "function", "defer_loading": True, "function": get_weather_schema}, | |
| ] | |
| messages.append({ | |
| "role": "tool", | |
| "tool_call_id": call_id, | |
| "content": [ | |
| {"type": "text", "text": "Found 1 tool."}, | |
| {"type": "tool_reference", "name": "get_weather"}, | |
| ], | |
| }) | |
| ``` | |
| Your harness implements and runs the search. Keep the full `tools` list, including deferred tools, on every request. | |
| See [Deferred tools and tool search](https://docs.liquid.ai/lfm/key-concepts/tool-search) for the full guide. | |
| </details> | |
| ## Fine-tuning | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| LFM3-VL-2B is designed for **easy customization** for a given domain, task, or application via [TRL](https://docs.liquid.ai/lfm/fine-tuning/trl). | |
| <table style="width: 100%; display: table; border: 0; border-radius: 0; border-collapse: collapse;"> | |
| <thead style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Training</th> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Use case</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Notebook</th> | |
| </tr> | |
| </thead> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>SFT</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Extract structured JSON from receipt photos</td> | |
| <td style="text-align: center; border: 0; padding: 0.55em 0.75em;"><a href="https://colab.research.google.com/github/Liquid4All/cookbook/blob/main/finetuning/notebooks/lfm3_vl_sft_with_trl.ipynb" title="SFT with TRL"><img src="https://colab.research.google.com/assets/colab-badge.svg" width="117" height="20" alt="Open in Colab" style="display: inline-block; width: 117px; height: 20px; margin: 0; vertical-align: middle;" /></a></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;"><strong>GRPO</strong></td> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Transcribe images of equations to LaTeX</td> | |
| <td style="text-align: center; border: 0; padding: 0.55em 0.75em;"><a href="https://colab.research.google.com/github/Liquid4All/cookbook/blob/main/finetuning/notebooks/lfm3_vl_grpo_with_trl.ipynb" title="GRPO with TRL"><img src="https://colab.research.google.com/assets/colab-badge.svg" width="117" height="20" alt="Open in Colab" style="display: inline-block; width: 117px; height: 20px; margin: 0; vertical-align: middle;" /></a></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| ## Performance | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| ### Benchmarks | |
| Across 62 vision benchmarks, LFM3-VL-2B scores at least 8 points ahead of all models of similar size. It matches Gemma 4 12B, is within 2 points of GPT-5.6 Luna, and scores higher than Gemini 3.5 Flash Lite. | |
| <div role="region" aria-labelledby="benchmarks" tabindex="0" style="width: 100%; max-width: 100%; overflow-x: auto; -webkit-overflow-scrolling: touch;"> | |
| <table style="width: 100%; min-width: 48rem; display: table; border: 0; border-radius: 0; border-collapse: collapse; font-size: calc(0.875em - 1pt);"> | |
| <thead style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Category</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; background-color: rgba(108, 79, 224, 0.08); padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);"><strong>LFM3-VL<br>2B</strong></th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; background-color: rgba(108, 79, 224, 0.08); padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);"><strong>LFM3-VL<br>2B (no think)</strong></th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">LFM2.5-VL<br>3B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">MiniCPM-V 4.7<br>1B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Qwen3.5<br>2B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Qwen3.5<br>4B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">InternVL3.5<br>4B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemma 4<br>E2B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemma 4<br>12B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">GPT-5.6<br>Luna</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemini 3.5<br>Flash Lite</th> | |
| </tr> | |
| </thead> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">General</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">66.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">56.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>74.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>74.1</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Perception</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>75.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">68.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>77.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Document, OCR & Chart</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">83.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">71.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>85.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>84.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.3</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Math & logical reasoning</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">68.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">41.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">40.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>78.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>79.3</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.7</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Visual grounding</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>77.3</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">72.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>74.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Embodied reasoning</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>64.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">57.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>63.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.3</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">GUI understanding</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>83.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">81.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>82.5</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Video</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">54.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>72.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>70.0</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Multilingual</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">84.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">76.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>86.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>85.8</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Agentic</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">42.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">32.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">16.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">15.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">31.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">N/A</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">23.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>56.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>62.4</strong></td> | |
| </tr> | |
| </tbody> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);"><strong>Average</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">71.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">62.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">57.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">57.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">64.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);"><strong>73.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">61.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">53.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);"><u>71.7</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);"><strong>73.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em; border-top: 1px solid rgba(127, 127, 127, 0.25);">70.0</td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </div> | |
| <details> | |
| <summary><small>All 62 benchmarks</small></summary> | |
| <div role="region" aria-labelledby="benchmarks" tabindex="0" style="width: 100%; max-width: 100%; overflow-x: auto; -webkit-overflow-scrolling: touch;"> | |
| <table style="width: 100%; min-width: 56rem; display: table; border: 0; border-radius: 0; border-collapse: collapse; font-size: calc(0.875em - 1pt);"> | |
| <thead style="border: 0;"> | |
| <tr style="border: 0;"> | |
| <th scope="col" style="text-align: left; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Benchmark</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; background-color: rgba(108, 79, 224, 0.08); padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);"><strong>LFM3-VL<br>2B</strong></th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; background-color: rgba(108, 79, 224, 0.08); padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);"><strong>LFM3-VL<br>2B (no think)</strong></th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">LFM2.5-VL<br>3B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">MiniCPM-V 4.7<br>1B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Qwen3.5<br>2B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Qwen3.5<br>4B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">InternVL3.5<br>4B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemma 4<br>E2B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemma 4<br>12B</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">GPT-5.6<br>Luna</th> | |
| <th scope="col" style="text-align: center; white-space: nowrap; padding: 0.55em 0.75em; border: 0; border-bottom: 1px solid rgba(127, 127, 127, 0.55);">Gemini 3.5<br>Flash Lite</th> | |
| </tr> | |
| </thead> | |
| <tbody style="border: 0;"> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">General</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MME</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">86.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">76.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>88.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>89.2</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMStar</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">74.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">62.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>76.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>77.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.1</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">SimpleVQA</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">36.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">27.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">32.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">36.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">38.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">33.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">28.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">42.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>53.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>56.9</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">SEED-Bench (image)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">78.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">76.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>80.6</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>79.5</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMBench (dev EN v1.1)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">86.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">76.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>86.5</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">70.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>88.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>88.2</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMMU (val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">55.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">48.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>76.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>75.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMMU-Pro</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">45.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">35.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">33.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">38.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">42.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>69.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>70.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MM-Vet (v1)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">57.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">44.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>67.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>73.3</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MM-IFEval</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">72.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">54.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">60.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>83.0</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>82.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MuirBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">66.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>72.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">54.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>72.7</u></td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Perception</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">BLINK</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>71.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">68.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">60.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>70.9</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.9</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">CountBenchQA</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>93.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">86.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">92.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>95.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">91.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">90.1</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">HallusionBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">65.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">52.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>66.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>68.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.6</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">POPE</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">88.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">86.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>88.9</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>89.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>89.2</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">PerceptionBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">37.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">28.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">27.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">26.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">29.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">27.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">28.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>43.5</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>48.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.7</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">HR-Bench (4K)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>82.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>88.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">55.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">HR-Bench (8K)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>76.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">64.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>82.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">54.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">70.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">60.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.7</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ZoomBench (full + crop average)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>62.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">60.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>65.0</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">V*Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>86.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">80.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>89.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.9</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">RealWorldQA</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>79.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">73.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>81.0</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.4</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">CV-Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>88.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">85.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>88.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.7</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Document, OCR & Chart</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">DocVQA (val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">96.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">94.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">91.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">91.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">95.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>97.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">90.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">90.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>97.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">94.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">96.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">TextVQA (val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">87.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">85.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>90.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>88.9</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">OCRBench v1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>86.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">82.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>87.9</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">OCRBench v2 (En)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">63.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">48.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">55.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>65.7</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>67.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">55.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ChartQA (test)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>92.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">81.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">89.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>90.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">InfographicVQA (val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">86.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">70.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>90.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">89.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>92.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">CharXiv (descriptive, val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">87.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">65.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">84.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">92.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>95.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>94.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">CharXiv (reasoning, val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">70.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">44.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">38.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>77.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>73.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.2</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Math & logical reasoning</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">LogicVista</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">60.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">30.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">34.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">54.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>76.3</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>74.7</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MATH-Vision (full)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">51.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">28.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">22.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">30.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">33.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">40.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>73.8</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>79.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MathVista (mini)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>84.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">68.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>84.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.7</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">We-Math (testmini, strict)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">68.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">20.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">23.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>81.0</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">26.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>78.2</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">70.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.1</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">DynaMath (average accuracy)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">79.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">57.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>84.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>87.6</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>84.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.2</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Visual grounding</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">RefCOCO-avg</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>90.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">87.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>88.8</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.6</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">RefCOCO-M</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>95.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">92.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">94.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">92.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">90.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">93.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>94.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">89.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.6</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Point-Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>73.8</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">69.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">16.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">54.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">14.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>73.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.4</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">RefSpatial-Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">49.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">40.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">32.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">8.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">30.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">23.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">6.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>51.7</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>52.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">33.6</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Embodied reasoning</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">EmbSpatial-Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>82.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">77.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>82.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.3</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ERQA</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">48.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">40.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>59.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>56.5</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MindCube (tinybench)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>56.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">51.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>54.9</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">37.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">SAT (val + test)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>80.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>80.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">74.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.8</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">RoboSpatial-Home</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">63.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">51.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>67.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">46.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>66.9</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.4</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Where2Place</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">44.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">42.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">42.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">6.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">30.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">24.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">18.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>49.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>51.6</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">OpenEQA (episodic memory, video)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">76.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">66.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">49.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">60.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>78.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>77.5</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">VSI-Bench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>63.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>63.3</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">26.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">30.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">31.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">49.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">36.5</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">GUI understanding</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ScreenSpot-Pro</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>55.5</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">49.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">22.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">4.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">38.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">1.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">25.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>57.4</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.2</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ScreenSpot-v2 Desktop</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>94.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>95.5</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">91.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">93.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>94.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">86.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ScreenSpot-v2 Mobile</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">92.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">91.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>92.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">87.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>93.0</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">88.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">80.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ScreenSpot-v2 Web</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>89.9</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">89.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">89.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>92.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">89.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.3</td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Video</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MVBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">69.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">59.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>71.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>72.3</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">54.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.5</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">ActivityNet-QA (test)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><strong>71.2</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">59.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">40.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>66.8</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.6</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">LVBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">41.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">40.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">34.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">39.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">35.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">42.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">27.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">36.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>58.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>58.7</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MLVU (dev, M-Avg)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">71.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">63.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">64.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">66.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>77.6</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>78.2</strong></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMVU (val)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">52.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">45.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">38.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">45.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">67.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">52.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">47.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>77.6</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>76.3</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MotionBench (dev)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;"><u>64.0</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">56.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">56.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">41.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">53.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>67.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.0</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Video-MME (v1, no subtitles)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">62.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">57.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">44.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">71.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">61.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">48.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>75.7</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>74.0</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Video-MME (v1, subtitles)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">69.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">63.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">62.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">65.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>78.3</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">63.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">59.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">73.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>81.6</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">77.8</td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Video-MMMU</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">49.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">39.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">22.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">50.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">51.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">69.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">58.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">57.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">72.7</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>81.1</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>73.9</u></td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Multilingual</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MMMB</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">85.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">80.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">83.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.4</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">85.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">81.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">78.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>86.9</strong></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>85.4</u></td> | |
| </tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">Multilingual MMBench</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">83.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">72.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">79.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">75.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">76.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">68.0</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>85.4</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">82.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>86.2</strong></td> | |
| </tr> | |
| <tr style="border: 0;"><th scope="rowgroup" style="text-align: left; background-color: transparent; padding: 0.55em 0.75em; border: 0; font-weight: 600; padding-top: 1em; padding-bottom: 0.5em;">Agentic</th><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td aria-hidden="true" style="border: 0; padding: 0.55em 0.75em; background-color: rgba(108, 79, 224, 0.08);"></td><td colspan="9" aria-hidden="true" style="border: 0; padding: 0.55em 0.75em;"></td></tr> | |
| <tr style="border: 0;"> | |
| <td style="border: 0; padding: 0.55em 0.75em;">MM-ToolSandbox (partial credit)</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">42.5</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; background-color: rgba(108, 79, 224, 0.08); border: 0; padding: 0.55em 0.75em;">32.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">21.1</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">16.9</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">15.2</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">31.3</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">N/A</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">23.8</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;">43.6</td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><u>56.1</u></td> | |
| <td style="text-align: center; font-variant-numeric: tabular-nums; border: 0; padding: 0.55em 0.75em;"><strong>62.4</strong></td> | |
| </tr> | |
| </tbody> | |
| </table> | |
| </div> | |
| </details> | |
| <details> | |
| <summary><small>Evaluation details</small></summary> | |
| <p><small>We evaluated all models with vLLM 0.27.1, using each model's recommended generation parameters when available.</small></p> | |
| <p><small>We used reasoning mode for all models except LFM2.5-VL-3B, which does not support it, and the LFM3-VL-2B no-thinking configuration, for which we disabled thinking. For InternVL3.5, we report the higher score from reasoning and non-reasoning modes on each benchmark. GPT-5.6 Luna and Gemini 3.5 Flash Lite used their default reasoning effort: medium for Luna and minimal for Gemini.</small></p> | |
| <p><small>For models without native video support, we sampled frames at 2 FPS, up to a maximum of 384 frames per video, and provided them to the model as images.</small></p> | |
| <p><small>All scores are normalized to a 0–100 scale. Each category score is the unweighted mean of its benchmark scores, and the Average row is the unweighted mean across all 62 benchmarks.</small></p> | |
| <p><small>We used GPT-6 Luna as a judge for benchmarks that require an LLM judge.</small></p> | |
| <p><small> | |
| <strong>Original score scales:</strong> MME uses a 0–2800 scale; OCRBench, 0–1000; and DocVQA and InfographicVQA, 0–1.<br> | |
| <strong>RefCOCO-avg:</strong> Mean P@1 across eight splits: RefCOCO (val, testA, testB), RefCOCO+ (val, testA, testB), and RefCOCOg (val, test).<br> | |
| <strong>POPE:</strong> F1 over all examples from the adversarial, popular, and random subsets.<br> | |
| <strong>MMMU-Pro:</strong> The multiple-choice variant with 10 answer options per question. | |
| </small></p> | |
| </details> | |
| ### Edge inference | |
| LFM3-VL-2B has the highest prefill throughput and the lowest memory use of all compared models on all three devices. | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/64df8592d27135dd568380b5/ZK7GqqnM_3E4U0AW7Ns_O.png" alt="LFM3-VL-2B edge inference: prefill throughput, decode throughput, and memory on AMD Ryzen AI Max+ 395, Apple M5 Max, and Samsung Galaxy S26 Ultra, compared with LFM2.5-VL-3B, MiniCPM-V 4.7 1B, Qwen3.5-2B, and Gemma 4 E2B." width="1989" height="1999" style="width: 100%; max-width: 995px; height: auto;" /> | |
| <details> | |
| <summary><small>Evaluation details</small></summary> | |
| <p><small>All models run in llama.cpp with a Q4_0 GGUF language model and an F16 vision projector (mmproj). Each request has one 512×512 image and 1,024 text tokens, and generates 256 tokens. Prefill is the prompt processing speed and decode is the generation speed, both in tokens per second. Memory is peak use in GB.</small></p> | |
| </details> | |
| ### GPU inference | |
| On one NVIDIA B300, LFM3-VL-2B produces more than 12,000 tokens/s at 1,024 concurrent requests, more than any compared model. | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/64df8592d27135dd568380b5/lXRtpri8b7R9MuwlKtQtt.png" alt="LFM3-VL-2B GPU inference: end-to-end output throughput versus concurrent requests on one NVIDIA B300, compared with Qwen 3.5 2B, MiniCPM-V 4.7 1B, Gemma 4 E2B, and LFM2.5-VL-3B." width="1440" height="749" style="width: 100%; max-width: 1440px; height: auto;" /> | |
| <details> | |
| <summary><small>Evaluation details</small></summary> | |
| <p><small>All models run in BF16 on SGLang v0.5.22 with LFM3 support. Each request has one 512×512 image and 1,024 text tokens, and generates at most 256 tokens. Throughput is end-to-end output tokens per second, as the mean of 3 runs.</small></p> | |
| </details> | |
| ## Training | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/64df8592d27135dd568380b5/VRo1ZLQhR_aw0tpC6B707.png" alt="LFM3-VL-2B pre-training: LFM3-1.7B-Base is pre-trained on web and synthetic data (about 15T tokens), then code, math, and science (3T tokens at 4K context), then mid-trained on curated agentic data (3T tokens at 32K context), a 128K extension (500B tokens), and a 256K extension (50B tokens), for 22T tokens in total." width="3344" height="896" style="width: 100%; max-width: 1672px; height: auto;" /> | |
| **Pre-training:** LFM3-VL-2B starts from [LFM3-1.7B-Base](https://huggingface.co/LiquidAI/LFM3-1.7B-Base), which is pre-trained in two stages on 22T tokens in total. | |
| - **Main pre-training:** compared with LFM2, the mix adds more scientific papers, repository-level code, math, and a wider range of knowledge sources. | |
| - **Mid-training:** the last 3.5T tokens use curated, higher-quality data with a larger share of agentic traces and tool calls. This stage also extends the context window to 256K tokens. | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/64df8592d27135dd568380b5/p36YCBS_lG7tinntf-VNB.png" alt="LFM3-VL-2B post-training: LFM3-1.7B-Base and the Liquid vision encoder go through vision mid-training and SFT, then vision RL. MOPD distills the vision RL model and the Mixed RL model from LFM3-1.7B into LFM3-VL-2B." width="2776" height="1376" style="width: 100%; max-width: 1388px; height: auto;" /> | |
| **Post-training:** four stages develop visual understanding, reasoning, and tool use. | |
| - **Vision mid-training:** LFM3-1.7B-Base is joined with our new in-house vision encoder, which combines convolution and attention, and trained on image and video data. | |
| - **Supervised fine-tuning (SFT):** a wide mix of instruction following, reasoning, tool calling, agentic traces, grounding, and multimodal perception and understanding. | |
| - **Vision reinforcement learning:** many domains trained at once, to improve reasoning and general intelligence. | |
| - **Multi-domain on-policy distillation (MOPD):** a vision teacher model and the Mixed RL model from LFM3-1.7B are distilled back into a single model. | |
| ## Citation | |
| <hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" /> | |
| ```bibtex | |
| @article{liquidAI2026LFM3, | |
| author = {Liquid AI}, | |
| title = {Introducing LFM3: Every Modality for Specialized Intelligence}, | |
| journal = {Liquid AI Blog}, | |
| year = {2026}, | |
| note = {www.liquid.ai/blog/lfm3}, | |
| } | |
| ``` | |
| For questions and feedback, join [Discord](https://discord.com/invite/liquid-ai). For custom deployment and fine-tuning support, [contact Liquid AI](https://www.liquid.ai/connect?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface). | |