---
tags:
- kimi-k3.1-pro
- kimi-k3.1
- kimi
- k3.1-pro
license: other
license_name: kimi-k3.1-pro
library_name: transformers
pipeline_tag: image-text-to-text
language:
- af
- am
- ar
- as
- ast
- az
- be
- bg
- bn
- bs
- ca
- ceb
- ckb
- cs
- cy
- da
- de
- el
- en
- es
- et
- eu
- fa
- ff
- fi
- fil
- fr
- ga
- gl
- gn
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- ig
- is
- it
- ja
- jv
- ka
- kam
- kea
- kk
- km
- kmr
- kn
- ko
- ky
- lb
- lg
- ln
- lo
- lt
- luo
- lv
- mi
- mk
- ml
- mn
- mr
- ms
- mt
- mvy
- my
- ne
- nl
- 'no'
- nso
- ny
- oc
- om
- or
- pa
- pl
- ps
- pt
- qxp
- ro
- ru
- rw
- sd
- sk
- skr
- sl
- sn
- so
- sr
- sv
- sw
- ta
- te
- tg
- th
- ti
- tk
- tr
- ug
- uk
- umb
- ur
- uz
- vi
- wo
- xh
- yo
- yue
- zh
- zu
base_model:
- moonshotai/Kimi-K3.1-Pro
---
β‘ Each donation funds the next large quant.
I host free GGUF or MoE quants as independent research.
Local hardware: Mechrevo Kuangshi GM7AG0M β RTX 3060 Laptop 6GB GDDR6, 64GB DDR5, i7-12700H (14C/20T, 4.7GHz), Windows 11, Samsung 990 Pro.
Good for imatrix and 0.6β35B-class work in RAM. 9B+ and searches need rented H200/Blackwell, typically $100 per quant.
π Boostyπ¦ Β |Β
β Buy Me a Coffeeπ¦ Β |Β
β DonationAlertsπ¦
π Thanks to Hugging Face for extra storage.π¦
---
## NOESIS / AMAImedia
Released as part of the **NOESIS Professional Multilingual Dubbing Automation Platform**
(framework: DHCF-FNO β Deterministic Hybrid Control Framework for Frozen Neural Operators).
- **Founder:** Ilia Bolotnikov
- **Organization:** [AMAImedia.com](https://www.amaimedia.com)
- **X (Twitter):** [@AMAImediacom](https://x.com/AMAImediacom)
- **LinkedIn:** [Ilia Bolotnikov](https://www.linkedin.com/in/ilia-bolotnikov)
- **Telegram:** [@AMAImediacom](https://t.me/AMAImediacom)
- **Release date:** 2026-11-05
---
π° Tech Blog | π API Quickstart
## 1. Model Introduction
Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, Kimi K3.1 Pro delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and other agentic capabilities.
## 2. Model Summary
| Architecture |
Mixture-of-Experts (MoE) |
| Total Parameters |
2.8T |
| Activated Parameters |
104B |
| Number of Layers |
93 |
| Number of Dense Layers |
1 |
| Attention-Layer Composition |
69 KDA + 24 Gated DSA* |
| Attention Hidden Dimension |
7168 |
| Number of Attention Heads |
96 |
| DSA Index Head Dimension |
128 |
| DSA Index Number of Heads |
32 |
| DSA Index Top-K |
2048 |
| Latent MoE Dimension |
3584 |
| MoE Hidden Dimension (per Expert) |
3072 |
| Number of Experts |
896 |
| Selected Experts per Token |
16 |
| Number of Shared Experts |
2 |
| Vocabulary Size |
160K |
| Context Length |
1048576 |
| Attention Mechanism |
KDA & Gated DSA |
| Activation Function |
SiTU-GLU |
| Vision Encoder |
MoonViT-V2 |
| Parameters of Vision Encoder |
401M |
| Quantization |
MXFP4 weights / MXFP8 activations
(quantization-aware training) |
| Modality |
Text, Image |
* Compared with Kimi K3, we replace the full-attention Gated MLA layers with Gated DeepSeek Sparse Attention (Gated DSA) layers for more efficient long-context modeling.
## 3. Evaluation Results
Unless otherwise specified, all Kimi K3.1 Pro results use reasoning effort `max`, `temperature = 1.0`, and `top-p = 0.95`. A dash (`β`) means that the source table does not report a score. Higher scores are better except where the benchmark name explicitly states `lower is better`; Elo scores and other benchmark-specific metrics are not directly comparable with accuracy or pass-rate scores.
| Benchmark |
Kimi K3.1 Pro
(max) |
Claude Fable 5.1
(max, w/ fallback) |
GPT-6 Astra
(max, w/ fallback) |
Claude Opus 5.5
(max, w/ fallback) |
DeepSeek-V4.1-Flash-1017
(max) |
GLM-5.3
(max) |
| Coding |
| Terminal-Bench 4.0 |
65.7 |
57.9 |
58.2 |
66.4 |
42.3 |
41.8 |
| Terminal-Bench-Science 0.1 |
38.1 |
40.0 |
68.1 |
63.3 |
15.7 |
8.1 |
| SWE Marathon v1.1 |
51.7 |
45.6 |
42.5 |
46.3 |
40.0 |
42.5 |
| BenchCAD w/o tools |
72.8 |
60.6 |
β |
73.0 |
41.2 |
β |
| BenchCAD w/ tools |
92.7 |
92.6 |
95.9 |
96.2 |
81.6 |
β |
| Program Bench |
31.5 |
53.5 |
50.0 |
65.0 |
29.1 |
19.0 |
| DeepSWE v1.1 |
75.5 |
67.4 |
74.1 |
74.2 |
77.0 |
66.9 |
| PostTrain Bench v1.2 |
36.5 |
44.6 |
41.9 |
43.8 |
30.5 |
34.5 |
| Kimi Code Bench 2.0 (Internal) |
77.1 |
β |
β |
β |
76.1 |
61.7 |
| Kimi Code Bench 3.0 Long-horizon (Internal) |
61.2 |
58.8 |
66.5 |
58.5 |
51.5 |
45.5 |
| Agentic |
| HLE-Full w/ tools |
70.0 |
65.6 |
57.2 |
67.7 |
58.8 |
62.5 |
| BrowseComp |
92.1 |
β |
91.5 |
90.8 |
β |
β |
| BioMysteryBench |
80.6 |
81.6 |
78.9 |
81.9 |
80.0 |
79.6 |
| CharXiv (RQ) w/ python |
93.4 |
92.7 |
92.8 |
93.8 |
85.6 |
β |
| MMMU-Pro w/ python |
90.0 |
88.4 |
87.8 |
89.8 |
82.5 |
β |
| GDP.pdf w/ python |
85.7 |
83.8 |
85.5 |
83.9 |
73.0 |
β |
| ChartoGraphy w/ python |
90.2 |
88.4 |
91.0 |
89.0 |
83.0 |
β |
| BabyVision w/ python |
95.4 |
95.1 |
96.6 |
97.7 |
92.5 |
β |
| ZeroBench_main w/ python (pass@5) |
63.0 |
59.0 |
58.0 |
61.0 |
51.0 |
β |
| Agents' Last Exam (ALL) |
43.2 |
β |
41.8 |
42.6 |
37.7 |
26.2 |
| Agents' Last Exam (CLI) |
44.2 |
β |
44.2 |
40.7 |
36.0 |
29.4 |
| Automation Bench-AA |
73.3 |
59.4 |
68.5 |
69.5 |
66.6 |
62.2 |
| GDPval-AA v2.1 (Elo-score) |
1846 |
1754 |
1573 |
1866 |
1746 |
1650 |
| AA-Briefcase v1.1 (Elo-score) |
1678 |
1672 |
1569 |
1803 |
1570 |
1507 |
| APEX-Agents |
69.4 |
68.6 |
64.7 |
73.5 |
69.8 |
56.6 |
| OfficeQA Pro v2 |
64.4 |
54.5 |
54.4 |
62.2 |
40.4 |
31.1 |
| OfficeQA Pro |
67.4 |
68.6 |
66.2 |
β |
62.4 |
58.6 |
| Frontier Finance |
58.6 |
60.8 |
45.0 |
56.7 |
54.5 |
57.5 |
| Harvey Legal Agent |
23.7 |
19.1 |
β |
β |
21.0 |
β |
| HANDBOOK.md |
44.6 |
38.8 |
β |
41.5 |
28.9 |
20.8 |
| OSWorld V2.1 |
79.6 |
80.7 |
75.8 |
81.8 |
69.3 |
β |
| Business Operation (Internal) |
37.8 |
30.7 |
32.3 |
β |
8.9 |
18.6 |
| DECK-Arena (Internal, Elo-score) |
1456 |
β |
1423 |
1253 |
1231 |
1119 |
| Design Bench (Internal, Elo-score) |
957 |
β |
1076 |
927 |
863 |
718 |
| Kimi Hallu Bench Hard w/ tools (Internal, lower is better) |
8.3 |
23.3 |
5.5 |
15.0 |
23.3 |
22.6 |
| Reasoning & Knowledge & Multimodal |
| GDP.pdf |
34.6 |
27.6 |
34.2 |
30.6 |
17.2 |
11.2 |
| HLE-Full |
51.1 |
57.6 |
53.6 |
59.8 |
42.6 |
43.0* |
| HLE-Diamond |
39.4 |
55.1 |
65.8 |
60.9 |
21.6 |
25.1* |
| GPQA-Diamond |
94.2 |
93.7 |
96.1 |
93.9 |
92.2 |
91.7 |
| CharXiv (RQ) |
89.0 |
88.8 |
90.0 |
92.1 |
77.0 |
β |
| MMMU-Pro |
84.1 |
86.3 |
86.9 |
87.7 |
80.6 |
β |
| ZeroBench_main (avg@5 / pass@5) |
29.8 / 39.0 |
23.0 / 35.0 |
43.2 / 52.0 |
35.0 / 43.0 |
11.8 / 23.0 |
β |
| PerceptionBench |
68.3 |
63.0 |
77.6 |
72.1 |
47.7 |
β |
| Kimi Hallu Bench w/o tools (Internal, lower is better) |
5.4 |
11.4 |
4.2 |
6.8 |
13.1 |
14.8 |
| Cyber Security |
| ExploitBench |
74.7 |
83.0 |
100 |
91.0 |
β |
54.4 |
| ExploitGym |
20.7 |
30.4 |
42.4 |
34.5 |
β |
15.0 |
| xdev-bench-hard (Internal) |
81.0 |
β |
β |
β |
85.7 |
57.1 |
Evaluation Footnotes
#### Coding benchmarks
1. **Terminal-Bench 4.0.** Kimi K3.1 Pro is evaluated with the Claude Code harness. The DeepSeek-V4.1-Flash-1017 score is taken from its [release blog](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017). All remaining scores are the maximum values reported in model blog posts or on the [official Terminal-Bench leaderboard](https://www.tbench.ai/).
2. **Terminal-Bench-Science 0.1.** Kimi K3.1 Pro is evaluated with Claude Code. Internal evaluation of DeepSeek-V4.1-Flash-1017 yields 9.3; the table instead reports 15.7 for the older DeepSeek-V4.1-Flash from the official leaderboard. All remaining scores are from the [Terminal-Bench-Science leaderboard](https://www.terminal-bench-science.ai/).
3. **SWE-Marathon v1.1.** Kimi K3.1 Pro and DeepSeek-V4.1-Flash-1017 are evaluated with Claude Code. Other scores are from the [official leaderboard](https://www.swe-marathon.org/).
4. **ProgramBench.** The table reports binary scores: a task receives 1 if its ProgramBench score is at least 95%, and 0 otherwise. K3.1 Pro is evaluated with Claude Code. DeepSeek and GLM scores are taken from the [DeepSeek release blog](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017); remaining scores are from [Vals AI](https://www.vals.ai/benchmarks/programbench).
5. **DeepSWE v1.1.** K3.1 Pro is evaluated with Claude Code. Other scores come from the respective technical reports for [GPT-6 Astra](https://openai.com/index/gpt-6-astra/), [Claude Opus 5.5](https://www.anthropic.com/claude-opus-5-5-system-card), [Claude Fable 5.1](https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card), [DeepSeek-V4.1-Flash-1017](https://api-docs.deepseek.com/news/news261017/), and [GLM-5.3](https://z.ai/blog/glm-5.3).
6. **PostTrainBench.** K3.1 Pro and DeepSeek-V4.1-Flash-1017 are evaluated internally on v1.2 with Claude Code and H20 GPUs rather than H100 GPUs. For stable evaluation, all judge models use DeepSeek-V4.1-Flash-1017 at maximum effort, which best matched the official GPT-5.6-Terra (xhigh) judge in testing. Other scores are from the [official leaderboard](https://posttrainbench.com/).
7. **Kimi Code Bench 2.0 and Kimi Code Bench 3.0 Long-horizon.** These are internal benchmarks. K3.1 Pro is evaluated with Claude Code; all other models use their maximum-effort setting. Proprietary-model testing may involve fallback behavior.
8. **BenchCAD.** Open models are evaluated on 1,000-case subsets randomly sampled from the 17,900-case Vision2Code dataset at maximum reasoning effort. With-tools results use Claude Code; without-tools results use single-shot generation with official prompts and scoring. Claude scores are from the Opus 5.5 System Card, and GPT-6 Astra's with-tools score is from its official report. GPT-6 Astra has no reported without-tools score.
#### Agentic benchmarks
1. **BioMysteryBench.** Uses the [official v11 release](https://huggingface.co/datasets/Anthropic/BioMysteryBench-full/commit/b5a889c), with Kimi K3 as judge. K3.1 Pro uses Kimi Code; GLM-5.3 and DeepSeek-V4.1-Flash-1017 use Claude Code; GPT-6 Astra uses Codex. Claude scores are from official system cards.
2. **Agents' Last Exam.** Uses the [official v1.1 release](https://github.com/rdi-berkeley/agents-last-exam), comprising 122 tasks, including 86 CLI tasks. Runs that bypass stated requirements receive zero. DeepSeek and Kimi are evaluated with Claude Code and Kimi Code, respectively; other results are from the official benchmark website.
3. **OfficeQA Pro and OfficeQA Pro v2.** GPT-6 Astra uses Codex; other models use Claude Code. Each task provides the complete PDF corpus as page images without machine-readable text. External-model trajectories that retrieve reference answers online receive zero for those tasks.
4. **Frontier Finance.** Evaluated with the official Finance Agent v2 harness.
5. **HANDBOOK.md.** Evaluated with the official OpenHands-based harness, using tasks from the benchmark's early open-source v1 release.
6. **Harvey Legal Agent.** Evaluated on 1,251 public tasks with Artificial Analysis's Stirrup harness. The reported score is the all-pass rate: the percentage of tasks passing every rubric criterion.
7. **OSWorld V2.1.** Kimi models use the Kimi Agent harness in the official OSWorld v2 repository. GPT-6 Astra's score is taken from Muse Wonder's technical report.
8. **DECK-Arena and Design Bench.** DECK-Arena evaluates presentation generation on real-world queries; Design Bench covers graphic design through direct and reference-image few-shot prompting. Both evaluate python-pptx, pptxjs, and Kimi's in-house DSL in a harness with integrated search and image generation. The automated grader is calibrated on more than 10,000 human judgments.
9. **BrowseComp.** Uses context compaction triggered at 200K tokens and a 500-step maximum. If the limit is reached, the agent is forced to answer before judging. All runs use `temperature = 1.0` and `top-p = 1.0`.
10. **GDPval-AA v2.1, AA-Briefcase v1.1, and AutomationBench-AA.** Scores are cited from [Artificial Analysis](https://artificialanalysis.ai/). **APEX-Agents.** Scores are cited from the [official leaderboard](https://www.mercor.com/apex/apex-agents-leaderboard/).
11. **Tool-augmented multimodal evaluations.** GDP.pdf w/ python, ZeroBench w/ python, and ChartoGraphy w/ python are averaged over five runs; other multimodal benchmarks with Python are averaged over four. For GDP.pdf w/ python, each original PDF is sent to a sandbox for IPython processing. Responses are graded against each rubric criterion using Gemini-3.5-Flash at medium reasoning effort and the official judging prompt. The reported score is the task-macro mean rubric pass rate.
#### Reasoning, knowledge, and multimodal benchmarks
1. **GDP.pdf.** Each PDF is provided as page images resized to a longest edge of 1,152 pixels, interleaved with Docling-extracted text in page order. Responses are graded against each rubric criterion using Gemini-3.5-Flash Medium and the official judging prompt. The table reports the strict pass rate among fully scored responses. GLM-5.3 Max and DeepSeek-V4.1-Flash-1017 Max scores are cited from [Artificial Analysis](https://artificialanalysis.ai/).
2. **HLE-Full and HLE-Diamond.** The full evaluation sets contain 2,500 and 1,000 questions, respectively. For scores marked `*`, accuracy is reported on the text-only subset.
3. **Run counts.** GDP.pdf, ZeroBench, and ChartoGraphy are averaged over five runs; other multimodal benchmarks are averaged over four.
4. **MMMU-Pro.** Evaluated using the official protocol, preserving the original input order and prepending images to the text input.
5. **PerceptionBench.** An in-house benchmark focused on atomic visual perception capabilities.
6. **Kimi Hallucination Benchmark.** Evaluates factual accuracy on an internal set of challenging, de-identified prompts drawn from practical work tasks. The table reports claim-level hallucination rates assessed by fact-checking agents.
#### Cybersecurity benchmarks
1. **ExploitBench.** K3.1 Pro is evaluated with the official harness under a 300-turn budget. The table reports the pass@5 maximum-capability score: for each environment, the best of five seeds is scored by capability flags reached out of 16; arbitrary code execution counts as all 16 capabilities. Comparison scores are from [OpenAI](https://openai.com/index/gpt-6-astra/), [Anthropic](https://www.anthropic.com/claude-opus-5-5-system-card), and [GLM-5.3](https://z.ai/blog/glm-5.3).
2. **ExploitGym.** K3.1 Pro is evaluated with Kimi Code under a six-hour wall-clock budget per task. GPT-6 Astra, Claude, and GLM comparison scores are taken from their respective official reports, with Claude results using the same six-hour budget.
3. **xdev-bench-hard.** K3.1 Pro is evaluated with Kimi Code; GLM-5.3 and DeepSeek-V4.1-Flash-1017 use Claude Code. The internal benchmark contains expert-curated, source-code-based vulnerability discovery and exploitation tasks. The final model is evaluated at pass@3 over a random subset of runs, without hard timeouts or output-token limits.
## 4. Deployment and Availability
> [!Note]
> You can access Kimi K3.1 Pro's API on https://platform.kimi.ai by selecting `kimi-k3.1-pro`, and we provide OpenAI/Anthropic-compatible API for you.
> Currently, Kimi K3.1 Pro is recommended to run on the following inference engines:
- [vLLM](https://github.com/vllm-project/vllm) β see [recipes](https://recipes.vllm.ai/moonshotai/Kimi-K3.1-Pro)
- [SGLang](https://github.com/sgl-project/sglang) β see [cookbook](https://docs.sglang.io/cookbook/autoregressive/Moonshotai/Kimi-K3.1-Pro)
- [TokenSpeed](https://github.com/lightseekorg/tokenspeed) β see [recipes](https://lightseek.org/tokenspeed/recipes/models#kimi-k3-1-pro)
---
## 5. Model Usage
The thinking effort of Kimi K3.1 Pro is configured with the top-level `reasoning_effort` request field, which supports `"low"`, `"high"`, and `"max"` (default `"max"`).
For multi-turn conversations and tool calls, Kimi K3.1 Pro requires the complete assistant message returned by the API to be passed back to `messages` as-is β including `reasoning_content` and `tool_calls`, not just `content`:
```python
import openai
def chat_with_preserved_thinking(client: openai.OpenAI, model_name: str):
messages = [
{
"role": "user",
"content": "Tell me three random numbers."
},
{
"role": "assistant",
"reasoning_content": "I'll start by listing five numbers: 473, 921, 235, 215, 222, and I'll tell you the first three.",
"content": "473, 921, 235"
},
{
"role": "user",
"content": "What are the other two numbers you have in mind?"
}
]
response = client.chat.completions.create(
model=model_name,
messages=messages,
stream=False,
max_tokens=4096,
reasoning_effort="max",
)
# the assistant should mention 215 and 222 that appear in the prior reasoning content
print(f"response: {response.choices[0].message.reasoning}")
return response.choices[0].message.content
```
For full guides and examples (vision input, structured output, partial mode, tool choice, dynamic tool loading, context caching), see the [Kimi K3.1 Pro Quickstart](https://platform.kimi.ai/docs/guide/kimi-k3-1-pro-quickstart) and [Thinking Effort](https://platform.kimi.ai/docs/guide/use-thinking-effort).
## 6. License
Kimi K3.1 Pro is released under the [Kimi K3.1 Pro License](https://huggingface.co/moonshotai/Kimi-K3.1-Pro/blob/main/LICENSE).
## 7. Contact Us
If you have any questions,
please reach out at [support@moonshot.ai](mailto:support@moonshot.ai).
){kind=icon}
