rank,rank_stylectrl,model,openrouter_id,arena_score,95_pct_ci,votes,organization,license,knowledge_cutoff,url,displayed_name,pricing_source,id,description,pricing.prompt,pricing.completion,pricing.image,pricing
1,3,Gemini-2.5-Pro,google/gemini-2.5-pro,1404,+11/-11,7424,Google,Proprietary,not specified,http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro,google/gemini-2.5-pro,openrouter,google/gemini-2.5-pro,"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.",1.25e-06,1e-05,0.00516,0.00517125
2,4,GLM-4.5-Air,,1370,+18/-18,1425,Z.ai,MIT,not specified,https://z.ai/blog/glm-4.5,GLM-4.5-Air,free,,,,,,
3,4,GLM-4.5,,1370,+17/-17,1610,Z.ai,MIT,not specified,https://z.ai/blog/glm-4.5,GLM-4.5,free,,,,,,
4,6,Claude 3.7 Sonnet,anthropic/claude-3.7-sonnet,1357,+12/-12,7460,Anthropic,Proprietary,not specified,https://www.anthropic.com/news/claude-3-7-sonnet,anthropic/claude-3.7-sonnet,openrouter,anthropic/claude-3.7-sonnet,"Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. 

Claude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.

Read more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)",3e-06,1.5e-05,0.0048,0.004817999999999999
5,13,Gemini-2.5-Flash,google/gemini-2.5-flash,1291,+9/-9,8082,Google,Proprietary,not specified,http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-flash,google/gemini-2.5-flash,openrouter,google/gemini-2.5-flash,"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in ""thinking"" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. 

Additionally, Gemini 2.5 Flash is configurable through the ""max tokens for reasoning"" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).",3e-07,2.5e-06,0.001238,0.0012408
6,15,GPT-4.1-2025-04-14,openai/gpt-4.1,1250,+7/-7,11339,OpenAI,Proprietary,not specified,https://openai.com/index/gpt-4-1/,openai/gpt-4.1,openrouter,openai/gpt-4.1,"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.",2e-06,8e-06,0.0,9.999999999999999e-06
7,16,Claude 3.5 Sonnet (20241022),anthropic/claude-3.5-sonnet,1230,+7/-7,26267,Anthropic,Proprietary,2024/4,https://www.anthropic.com/news/3-5-models-and-computer-use,anthropic/claude-3.5-sonnet,openrouter,anthropic/claude-3.5-sonnet,"New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:

- Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding
- Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
- Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
- Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)

#multimodal",3e-06,1.5e-05,0.0048,0.004817999999999999
8,17,DeepSeek-R1,,1198,+15/-15,3755,DeepSeek,MIT,not specified,https://api-docs.deepseek.com/news/news250120,DeepSeek-R1,free,,,,,,
9,17,DeepSeek-V3-0324,,1196,+21/-21,1094,DeepSeek,MIT,not specified,https://api-docs.deepseek.com/news/news250325,DeepSeek-V3-0324,free,,,,,,
10,17,GPT-4.1-mini-2025-04-14,openai/gpt-4.1-mini,1190,+8/-8,9064,OpenAI,Proprietary,not specified,https://openai.com/index/gpt-4-1/,openai/gpt-4.1-mini,openrouter,openai/gpt-4.1-mini,"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.",4e-07,1.6e-06,0.0,2e-06
11,17,Qwen3-235B-A22B,,1186,+10/-10,5600,Alibaba,Apache 2.0,not specified,https://qwenlm.github.io/blog/qwen3/,Qwen3-235B-A22B,free,,,,,,
12,17,o3-2025-04-16,openai/o3,1185,+9/-9,5572,OpenAI,Proprietary,not specified,https://openai.com/index/introducing-o3-and-o4-mini/,openai/o3,openrouter,openai/o3,"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. ",2e-06,8e-06,0.00153,0.00154
13,17,Mistral Medium 3,mistralai/mistral-medium-3,1175,+9/-9,7511,Mistral,Proprietary,not specified,https://mistral.ai/news/mistral-medium-3,mistralai/mistral-medium-3,openrouter,mistralai/mistral-medium-3,"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.

The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.",4e-07,2e-06,0.0,2.4e-06
14,18,Grok-4-0709,x-ai/grok-4,1171,+10/-10,7067,xAI,Proprietary,not specified,https://docs.x.ai/docs/models/grok-4-0709,x-ai/grok-4,openrouter,x-ai/grok-4,"Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the [xAI docs](https://docs.x.ai/docs/models/grok-4-0709)",3e-06,1.5e-05,0.0,1.8e-05
15,24,Grok-3-Preview-02-24,x-ai/grok-3,1136,+10/-10,5764,xAI,Proprietary,not specified,https://x.ai/blog/grok-3,x-ai/grok-3,openrouter,x-ai/grok-3,"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.

",3e-06,1.5e-05,0.0,1.8e-05
16,24,Claude 3.5 Haiku (20241022),anthropic/claude-3.5-haiku,1132,+6/-6,22213,Anthropic,Proprietary,not specified,https://www.anthropic.com/news/3-5-models-and-computer-use,anthropic/claude-3.5-haiku,openrouter,anthropic/claude-3.5-haiku,"Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.

This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.

This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).",8e-07,4e-06,0.0,4.8e-06
17,24,Minimax-M1,,1128,+13/-13,3361,MiniMax,Apache 2.0,not specified,https://www.minimax.io/news/minimaxm1,Minimax-M1,free,,,,,,
18,26,o4-mini-2025-04-16,openai/o4-mini,1113,+9/-9,8850,OpenAI,Proprietary,not specified,https://openai.com/index/introducing-o3-and-o4-mini/,openai/o4-mini,openrouter,openai/o4-mini,"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.

Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.",1.1e-06,4.4e-06,0.0008415,0.000847
19,31,o1-2024-12-17,openai/o1,1040,+10/-10,9235,OpenAI,Proprietary,not specified,https://openai.com/index/o1-and-new-tools-for-developers/,openai/o1,openrouter,openai/o1,"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. 

The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).
",1.5e-05,6e-05,0.021675,0.02175
20,31,Llama-4-Maverick-17B-128E-Instruct,,1035,+11/-11,5474,Meta,Llama 4,not specified,https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct,Llama-4-Maverick-17B-128E-Instruct,free,,,,,,
21,35,DeepSeek-V3,,969,+12/-12,7699,DeepSeek,DeepSeek,not specified,https://huggingface.co/deepseek-ai/DeepSeek-V3,DeepSeek-V3,free,,,,,,
22,38,Llama-4-Scout-17B-16E-Instruct,,902,+27/-27,687,Meta,Llama,not specified,https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct,Llama-4-Scout-17B-16E-Instruct,free,,,,,,