Model catalog
Benchmarks
Arena Elo from free open daily snapshots on GitHub (text, code, vision, agent), plus a sparse Artificial Analysis subset OpenRouter embeds. One score set is cross-linked onto provider clones of the same model. Arena may score the same base model at different reasoning efforts, so those rows stay separate and link to the base model only when it exists in the catalog. The open dumps publish 20 models per Arena board (10 on agent), so a full board is short by design. Empty on a single board is a gap, not a ranking of zero.
| # | Model | Score |
|---|---|---|
| 1 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra | 61AA intelligence |
| 2 | xAI: Grok 4.6xAI · grok-4.6 · high effort | 61AA intelligence |
| 3 | Meta: Muse Spark 1.3Meta · muse-spark-1.3 · xhigh effort | 61AA intelligence |
| 4 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 | 53.4AA intelligence |
| 5 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 | 50.8AA intelligence |
| 6 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 49.6AA intelligence |
| 7 | OpenAI: GPT-5.6 SolOpenAI · gpt-5.6-sol | 47AA intelligence |
| 8 | Qwen3.8 Max 0902Alibaba · qwen3.8-max-0902 | 45.4AA intelligence |
| 9 | Mistral: GLM-5.3z-ai · glm-5.3 | 44.8AA intelligence |
| 10 | xAI: Grok 4.6x-ai · grok-4.6 | 44.3AA intelligence |
| 11 | Moonshot: Kimi K3moonshotai · kimi-k3 | 43.6AA intelligence |
| 12 | OpenAI: GPT-5.6 Terraopenai · gpt-5.6-terra | 42.1AA intelligence |
| 13 | Anthropic: Claude Opus 4.8 ThinkingAnthropic · claude-opus-4-8 | 41.8AA intelligence |
| 14 | Z.ai: GLM 5.3 FlashZ.ai · glm-5.3-flash | 41.8AA intelligence |
| 15 | Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash | 40.9AA intelligence |
| 16 | Qwen3.8 2.4T A95Bqwen · qwen3.8-2.4t-a95b | 39.9AA intelligence |
| 17 | Meta: Muse Spark 1.2meta · muse-spark-1.2 | 39.6AA intelligence |
| 18 | DeepSeek: V4.1 FlashDeepSeek · deepseek-v4.1-flash | 39.5AA intelligence |
| 19 | Google: Gemini 3.7 Flashgoogle · gemini-3.7-flash | 39.1AA intelligence |
| 20 | xAI: Grok 4.5xAI · grok-4.5 | 38.8AA intelligence |
| 21 | OpenAI: GPT-5.5OpenAI · gpt-5.5 | 38.4AA intelligence |
| 22 | Anthropic: Claude Sonnet 5 Thinkinganthropic · claude-sonnet-5 | 38.2AA intelligence |
| 23 | OpenAI: GPT-5.6 Lunaopenai · gpt-5.6-luna | 37.3AA intelligence |
| 24 | DeepSeek: V4 Pro 0813DeepSeek · deepseek-v4-pro-0813 | 36AA intelligence |
| 25 | DeepSeek: V4 Flash 0731deepseek · deepseek-v4-flash-0731 | 34.3AA intelligence |
| 26 | Google: Gemini 3.6 Flashgoogle · gemini-3.6-flash | 34AA intelligence |
| 27 | Mistral: GLM-5.2z-ai · glm-5.2 | 33.7AA intelligence |
| 28 | Meta: Muse Spark 1.1Meta · muse-spark-1.1 | 33.7AA intelligence |
| 29 | Qwen3.8 27BAlibaba · qwen3.8-27b | 33.7AA intelligence |
| 30 | Google: Gemini 3.5 Flashgoogle · gemini-3.5-flash | 32.6AA intelligence |
| 31 | DeepSeek: V4 Prodeepseek · deepseek-v4-pro | 30.4AA intelligence |
| 32 | Anthropic: Claude Sonnet 4.6 ThinkingAnthropic · claude-sonnet-4-6 | 30.1AA intelligence |
| 33 | Google: Gemini 3.1 Pro PreviewGoogle · gemini-3.1-pro-preview | 29.7AA intelligence |
| 34 | Qwen3.7 Maxqwen · qwen3.7-max | 29.5AA intelligence |
| 35 | MiniMax: M3minimax · minimax-m3 | 29.2AA intelligence |
| 36 | Moonshot: Kimi K2.6Moonshot · kimi-k2.6 | 27AA intelligence |
| 37 | Z.ai: GLM-5.1Z.ai · glm-5.1 | 26.1AA intelligence |
| 38 | MiMo V2.5 Proxiaomi · mimo-v2.5-pro | 26AA intelligence |
| 39 | Moonshot: Kimi K2.7 Codemoonshotai · kimi-k2.7-code | 25.8AA intelligence |
| 40 | Hy3 Previewtencent · hy3-preview | 25.3AA intelligence |
| 41 | Qwen3.7 Plusqwen · qwen3.7-plus | 25.2AA intelligence |
| 42 | NVIDIA: Inkling Thinkingthinkingmachines · inkling | 25AA intelligence |
| 43 | xAI: Grok 4.3x-ai · grok-4.3 | 24.9AA intelligence |
| 44 | Ling 3.0 Flash VLinclusionai · ling-3.0-flash-vl | 24.6AA intelligence |
| 45 | DeepSeek: V4 Flashdeepseek · deepseek-v4-flash | 24.2AA intelligence |
| 46 | OpenAI: GPT-5.4 Miniopenai · gpt-5.4-mini | 24.1AA intelligence |
| 47 | NVIDIA: Nemotron Ultranvidia · nemotron-3-ultra-550b-a55b | 22.9AA intelligence |
| 48 | MiniMax: M2.7minimax · minimax-m2.7 | 22.8AA intelligence |
| 49 | Ling 3.0 Flash Fininclusionai · ling-3.0-flash-fin | 22.6AA intelligence |
| 50 | Google: Gemini 3.5 Flash-Litegoogle · gemini-3.5-flash-lite | 22.2AA intelligence |
| 51 | Qwen3.6 27Bqwen · qwen3.6-27b | 21.4AA intelligence |
| 52 | Anthropic: Claude Sonnet 4.5anthropic · claude-sonnet-4.5 | 20.7AA intelligence |
| 53 | OpenAI: GPT-5.4 Nanoopenai · gpt-5.4-nano | 20.7AA intelligence |
| 54 | LongCat 2.0meituan · longcat-2.0 | 19.1AA intelligence |
| 55 | Qwen3.5 397B-A17Bqwen · qwen3.5-397b-a17b | 18.4AA intelligence |
| 56 | Qwen3.6 35B-A3Bqwen · qwen3.6-35b-a3b | 18.2AA intelligence |
| 57 | Anthropic: Claude Haiku 4.5 ThinkingAnthropic · claude-haiku-4.5 | 16.9AA intelligence |
| 58 | OpenAI: GPT-5 Miniopenai · gpt-5-mini | 16.8AA intelligence |
| 59 | Google: Gemini 2.5 ProGoogle · gemini-2.5-pro | 16.1AA intelligence |
| 60 | Google: Gemini 3.1 Flash Lite Previewgoogle · gemini-3.1-flash-lite-preview | 15.6AA intelligence |
| 61 | Qwen3.5 122B-A10Bqwen · qwen3.5-122b-a10b | 15.6AA intelligence |
| 62 | DeepSeek: V3.1 Terminusdeepseek · deepseek-v3.1-terminus | 14.8AA intelligence |
| 63 | Mistral: Medium 3.5mistralai · mistral-medium-3-5 | 14.2AA intelligence |
| 64 | Cohere: Command Acohere · command-a | 13.1AA intelligence |
| 65 | NVIDIA: Nemotron 3.5 Lightningnvidia · nemotron-3.5-lightning | 12.9AA intelligence |
| 66 | NVIDIA: Nemotron 3 Super 120B A12Bnvidia · nemotron-3-super-120b-a12b | 12.8AA intelligence |
| 67 | Qwen3 235B A22B Thinking 2507qwen · qwen3-235b-a22b-thinking-2507 | 12.7AA intelligence |
| 68 | OpenAI: gpt-oss-120bopenai · gpt-oss-120b | 11.6AA intelligence |
| 69 | DeepSeek: R1deepseek · deepseek-r1 | 11.4AA intelligence |
| 70 | Mistral: Small 4mistralai · mistral-small-2603 | 11.3AA intelligence |
| 71 | Granite 4.2 8Bibm-granite · granite-4.2-8b | 11.1AA intelligence |
| 72 | OpenAI: o3 Mini Highopenai · o3-mini-high | 11AA intelligence |
| 73 | Trinity Large Thinkingarcee-ai · trinity-large-thinking | 10.8AA intelligence |
| 74 | Cohere: North Mini Codecohere · north-mini-code | 9.9AA intelligence |
| 75 | Qwen3 30B A3B Thinking 2507qwen · qwen3-30b-a3b-thinking-2507 | 9.8AA intelligence |
| 76 | DeepSeek: V3 0324deepseek · deepseek-chat-v3-0324 | 9.7AA intelligence |
| 77 | Mistral: Large 3mistralai · mistral-large-2512 | 9.3AA intelligence |
| 78 | Mistral: Medium 3.1mistralai · mistral-medium-3.1 | 9.2AA intelligence |
| 79 | Qwen3 Coder Nextqwen · qwen3-coder-next | 9.2AA intelligence |
| 80 | OpenAI: GPT OSS 20Bopenai · gpt-oss-20b | 9AA intelligence |
| 81 | NVIDIA: Nemotron 3 Nano 30B A3Bnvidia · nemotron-3-nano-30b-a3b | 8.9AA intelligence |
| 82 | Mistral: Devstral 2mistralai · devstral-2512 | 8.6AA intelligence |
| 83 | Solar Pro 3upstage · solar-pro-3 | 7.8AA intelligence |
| 84 | Mistral: Ministral 3 14B 2512mistralai · ministral-14b-2512 | 6AA intelligence |
| 85 | Mistral: Ministral 3 8B 2512mistralai · ministral-8b-2512 | 5.5AA intelligence |
| 86 | Google: Gemma 3 27Bgoogle · gemma-3-27b-it | 4.9AA intelligence |
| 87 | Mistral: Ministral 3 3B 2512mistralai · ministral-3b-2512 | 4.8AA intelligence |
| 88 | Google: Gemma 3 12Bgoogle · gemma-3-12b-it | 3.8AA intelligence |
| 89 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 | 0AA intelligence |
| 90 | Anthropic: Claude Sonnet 4anthropic · claude-sonnet-4 | 0AA intelligence |
| 91 | DeepSeek: V3.2deepseek · deepseek-v3.2 | 0AA intelligence |
| 92 | Google: Gemma 3 4Bgoogle · gemma-3-4b-it | 0AA intelligence |
| 93 | Google: Gemma 4 26B A4Bgoogle · gemma-4-26b-a4b-it | 0AA intelligence |
| 94 | Google: Gemma 4 31Bgoogle · gemma-4-31b-it | 0AA intelligence |
| 95 | Z.ai: GLM-4.6z-ai · glm-4.6 | 0AA intelligence |
| 96 | Z.ai: GLM-4.7z-ai · glm-4.7 | 0AA intelligence |
| 97 | OpenAI: GPT-3.5 Turboopenai · gpt-3.5-turbo | 0AA intelligence |
| 98 | OpenAI: GPT-4openai · gpt-4 | 0AA intelligence |
| 99 | OpenAI: GPT-4 Turboopenai · gpt-4-turbo | 0AA intelligence |
| 100 | OpenAI: GPT-4.1 Miniopenai · gpt-4.1-mini | 0AA intelligence |
| 101 | OpenAI: GPT-4.1 Nanoopenai · gpt-4.1-nano | 0AA intelligence |
| 102 | OpenAI: GPT-4o (2024-05-13)openai · gpt-4o-2024-05-13 | 0AA intelligence |
| 103 | OpenAI: GPT-4o-miniopenai · gpt-4o-mini | 0AA intelligence |
| 104 | OpenAI: GPT-5openai · gpt-5 | 0AA intelligence |
| 105 | OpenAI: GPT-5.1openai · gpt-5.1 | 0AA intelligence |
| 106 | OpenAI: GPT-5.4OpenAI · gpt-5.4 | 0AA intelligence |
| 107 | xAI: Grok Build 0.1x-ai · grok-build-0.1 | 0AA intelligence |
| 108 | Inkling Smallthinkingmachines · inkling-small | 0AA intelligence |
| 109 | KAT-Coder-Pro V2kwaipilot · kat-coder-pro-v2 | 0AA intelligence |
| 110 | Moonshot: Kimi K2 0711moonshotai · kimi-k2-thinking | 0AA intelligence |
| 111 | Moonshot: Kimi K2.5moonshotai · kimi-k2.5 | 0AA intelligence |
| 112 | Ling 3.0 Flashinclusionai · ling-3.0-flash | 0AA intelligence |
| 113 | Meta: Llama 3.1 8B Instructmeta-llama · llama-3.1-8b-instruct | 0AA intelligence |
| 114 | Meta: Llama 3.3 70B Instructmeta-llama · llama-3.3-70b-instruct | 0AA intelligence |
| 115 | Meta: Llama 4 Maverickmeta-llama · llama-4-maverick | 0AA intelligence |
| 116 | Meta: Llama 4 Scoutmeta-llama · llama-4-scout | 0AA intelligence |
| 117 | Mercury 2inception · mercury-2 | 0AA intelligence |
| 118 | MiMo V2.5xiaomi · mimo-v2.5 | 0AA intelligence |
| 119 | NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoningnvidia · nemotron-3-nano-omni-30b-a3b-reasoning | 0AA intelligence |
| 120 | Amazon: Nova 2 Liteamazon · nova-2-lite-v1 | 0AA intelligence |
| 121 | OpenAI: o1openai · o1 | 0AA intelligence |
| 122 | Qwen3 14Bqwen · qwen3-14b | 0AA intelligence |
| 123 | Qwen3 32Bqwen · qwen3-32b | 0AA intelligence |
| 124 | Qwen3 8Bqwen · qwen3-8b | 0AA intelligence |
| 125 | Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))qwen · qwen3-next-80b-a3b-thinking | 0AA intelligence |
| 126 | Qwen3.5 35B-A3Bqwen · qwen3.5-35b-a3b | 0AA intelligence |
| 127 | Qwen3.5 9Bqwen · qwen3.5-9b | 0AA intelligence |
| 128 | Qwen3.6 Plusqwen · qwen3.6-plus | 0AA intelligence |
| 129 | Solar Pro 4upstage · solar-pro4 | 0AA intelligence |
| 130 | NVIDIA: Step 3.7 Flashstepfun · step-3.7-flash | 0AA intelligence |
Sources
Arena Elo from Arena AI, via open dumps by oolong-tea-2026. Artificial Analysis indices via OpenRouter (subset). Artificial Analysis for the indices themselves. Plus vendor-reported launch evals collected from announcements, analyst writeups, launch blogs, and community benchmarks. As of .
Turn benchmark scores into working sessions
Run agents in a local Git-enabled workspace, connect to another machine when needed, and track the sessions and tokens behind your work. See what your AI subscriptions covered.
Data and list-price estimates may contain mistakes. Not investment advice.