# Model capability rankings

Compare leading models on intelligence, coding, and overall ability. Scores are scaled so the current top mark is 100, then listed from high to low.

Append .md to this page’s address to get the Markdown text for programs and AI.

- `/en/rank.md`
- `/rank.md`

## Overall

A combined view of intelligence and coding ability

177 models

| Rank | Model | Model ID | Lab | Overall | Intelligence | Coding | Released | Age |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Claude Opus 5.5 | anthropic/claude-opus-5-5 | Anthropic | 100.0 | 98.9 | 100.0 | 2026-09-22 | 25 days |
| 2 | Claude Fable 5.1 | anthropic/claude-fable-5-1 | Anthropic | 98.1 | 98.6 | 96.2 | 2026-09-01 | 46 days |
| 3 | Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | Anthropic | 97.4 | 96.0 | 97.9 | 2026-09-28 | 19 days |
| 4 | Gemini 4 Argon | google/gemini-4-argon | Google | 97.3 | 100.0 | 92.6 | 2026-10-13 | 4 days |
| 5 | Claude Opus 5 | anthropic/claude-opus-5 | Anthropic | 96.7 | 98.4 | 93.3 | 2026-07-24 | 85 days |
| 6 | GPT-6 Astra | openai/gpt-6-astra | OpenAI | 96.6 | 94.1 | 98.3 | 2026-09-04 | 43 days |
| 7 | GPT-6.1 Sol | openai/gpt-6.1-sol | OpenAI | 96.3 | 94.5 | 97.2 | 2026-09-29 | 18 days |
| 8 | Muse Wonder | meta/muse-wonder-1.0 | Meta | 95.5 | 98.0 | 91.2 | 2026-10-12 | 5 days |
| 9 | Qwen3.7 Plus | alibaba/qwen3.7-plus | Alibaba | 95.5 | 94.9 | — | 2026-06-02 | 137 days |
| 10 | Qwen3.8 Max 0902 | alibaba/qwen3.8-max-0902 | Alibaba | 95.4 | 96.8 | 92.4 | 2026-09-02 | 45 days |
| 11 | Qwen3.8 Max | alibaba/qwen3.8-max | Alibaba | 95.4 | 96.8 | 92.3 | 2026-08-03 | 75 days |
| 12 | Muse Spark 1.3 | meta/muse-spark-1.3 | Meta | 95.3 | 97.2 | 91.6 | 2026-09-02 | 45 days |
| 13 | Kimi K3 | moonshotai/kimi-k3 | Moonshot AI | 94.6 | 96.2 | 91.4 | 2026-07-16 | 93 days |
| 14 | MiMo-V2.6-Pro | xiaomi/mimo-v2.6-pro | Xiaomi | 94.5 | 97.3 | 89.7 | 2026-09-22 | 25 days |
| 15 | Claude Fable 5 | anthropic/claude-fable-5 | Anthropic | 94.5 | 97.3 | 89.7 | 2026-06-09 | 130 days |
| 16 | Qwen3 Max Preview | alibaba/qwen3-max-preview | Alibaba | 94.5 | 93.9 | — | 2025-09-05 | 407 days |
| 17 | GLM-4.5 | zhipuai/glm-4.5 | Zhipu AI | 93.9 | 93.3 | — | 2025-07-28 | 446 days |
| 18 | DeepSeek R1 0528 | deepseek/deepseek-r1-0528 | DeepSeek | 93.8 | 93.2 | — | 2025-05-28 | 507 days |
| 19 | Gemini 3.8 Flash | google/gemini-3.8-flash | Google | 93.7 | 97.8 | 87.5 | 2026-09-02 | 45 days |
| 20 | GLM-5.3 | zhipuai/glm-5.3 | Zhipu AI | 93.6 | 96.0 | 89.5 | 2026-08-14 | 64 days |
| 21 | Gemini 3.7 Flash | google/gemini-3.7-flash | Google | 93.5 | 97.1 | 87.8 | 2026-08-13 | 65 days |
| 22 | MiMo-V2.6-Flash | xiaomi/mimo-v2.6-flash | Xiaomi | 93.5 | 95.0 | 90.3 | 2026-09-22 | 25 days |
| 23 | MiMo-V2-Omni | xiaomi/mimo-v2-omni | Xiaomi | 93.5 | 92.9 | — | 2026-03-18 | 213 days |
| 24 | GLM-5.3-Flash | zhipuai/glm-5.3-flash | Zhipu AI | 93.3 | 96.0 | 88.7 | 2026-08-26 | 52 days |
| 25 | DeepSeek V4.1 Flash | deepseek/deepseek-v4.1-flash | DeepSeek | 93.3 | 95.5 | 89.4 | 2026-09-10 | 37 days |
| 26 | Qwen3 VL 235B A22B Instruct | alibaba/qwen3-vl-235b-a22b-instruct | Alibaba | 93.3 | 92.7 | — | 2025-09-23 | 389 days |
| 27 | GLM-5.2 | zhipuai/glm-5.2 | Zhipu AI | 93.2 | 96.0 | 88.6 | 2026-06-13 | 126 days |
| 28 | GPT-5.5 Instant | openai/gpt-5.5-instant | OpenAI | 93.2 | 92.6 | — | 2026-05-05 | 165 days |
| 29 | DeepSeek V3.1 | deepseek/deepseek-chat-v3.1 | DeepSeek | 93.2 | 92.6 | — | 2025-08-21 | 422 days |
| 30 | DeepSeek-V3.1 | deepseek/deepseek-v3.1 | DeepSeek | 93.2 | 92.6 | — | 2025-08-21 | 422 days |
| 31 | Qwen3 235B-A22B Instruct 2507 | alibaba/qwen3-235b-a22b-instruct-2507 | Alibaba | 93.2 | 92.6 | — | 2025-07-21 | 453 days |
| 32 | GPT-5.6 Sol | openai/gpt-5.6-sol | OpenAI | 93.1 | 95.1 | 89.3 | 2026-07-09 | 100 days |
| 33 | Qwen3-Next 80B-A3B Instruct | alibaba/qwen3-next-80b-a3b-instruct | Alibaba | 93.1 | 92.5 | — | 2025-09 | 411 days |
| 34 | Gemini 2.5 Flash | google/gemini-2.5-flash | Google | 93.1 | 92.5 | — | 2025-06-17 | 487 days |
| 35 | Claude Opus 4.6 | anthropic/claude-opus-4-6 | Anthropic | 92.9 | 98.0 | 85.4 | 2026-02-05 | 254 days |
| 36 | Claude Opus 4.7 | anthropic/claude-opus-4-7 | Anthropic | 92.7 | 97.2 | 86.0 | 2026-04-16 | 184 days |
| 37 | GPT-6 Sol | openai/gpt-6-sol | OpenAI | 92.6 | 91.2 | 93.1 | 2026-09-22 | 25 days |
| 38 | Step 3.5 Flash | stepfun/step-3.5-flash | StepFun | 92.1 | 91.5 | — | 2026-01-29 | 261 days |
| 39 | Muse Spark 1.1 | meta/muse-spark-1.1 | Meta | 92.0 | 96.5 | 85.2 | 2026-04-08 | 192 days |
| 40 | Grok 4.6 | xai/grok-4.6 | xAI | 92.0 | 93.2 | 89.3 | 2026-08-12 | 66 days |
| 41 | Qwen3 VL 235B A22B Thinking | alibaba/qwen3-vl-235b-a22b-thinking | Alibaba | 92.0 | 91.4 | — | 2025-09-23 | 389 days |
| 42 | Muse Spark 1.2 | meta/muse-spark-1.2 | Meta | 91.9 | 96.8 | 84.7 | 2026-08-05 | 73 days |
| 43 | Qwen3.8 27B | alibaba/qwen3.8-27b | Alibaba | 91.9 | 94.0 | 88.0 | 2026-08-14 | 64 days |
| 44 | Gemini 3.6 Flash | google/gemini-3.6-flash | Google | 91.8 | 96.5 | 84.9 | 2026-07-21 | 88 days |
| 45 | Claude Opus 4.8 | anthropic/claude-opus-4-8 | Anthropic | 91.6 | 95.3 | 85.9 | 2026-05-28 | 142 days |
| 46 | Grok 4.7 | xai/grok-4.7 | xAI | 91.6 | 91.4 | 90.6 | 2026-09-21 | 26 days |
| 47 | DeepSeek V4 Flash | deepseek/deepseek-v4-flash | DeepSeek | 91.2 | 93.4 | 87.3 | 2026-04-24 | 176 days |
| 48 | GPT-5.3 Chat (latest) | openai/gpt-5.3-chat-latest | OpenAI | 91.2 | 90.6 | — | 2026-03-03 | 228 days |
| 49 | Grok 4.5 | xai/grok-4.5 | xAI | 91.1 | 94.5 | 85.7 | 2026-07-08 | 101 days |
| 50 | Step 5 Preview | stepfun/step-5-preview | StepFun | 91.1 | 94.1 | 86.3 | 2026-09-16 | 31 days |
| 51 | Gemini 3.5 Flash | google/gemini-3.5-flash | Google | 91.0 | 96.7 | 82.8 | 2026-05-19 | 151 days |
| 52 | GPT-5.5 | openai/gpt-5.5 | OpenAI | 90.9 | 96.0 | 83.5 | 2026-04-23 | 177 days |
| 53 | GLM-4.5-Air | zhipuai/glm-4.5-air | Zhipu AI | 90.8 | 90.3 | — | 2025-07-28 | 446 days |
| 54 | Claude Sonnet 4.6 | anthropic/claude-sonnet-4-6 | Anthropic | 90.7 | 95.1 | 84.1 | 2026-02-17 | 242 days |
| 55 | Qwen3.8 Flash Next | alibaba/qwen3.8-flash-next | Alibaba | 90.7 | — | 90.2 | 2026-08-27 | 51 days |
| 56 | Claude Sonnet 5 | anthropic/claude-sonnet-5 | Anthropic | 90.6 | 94.1 | 85.0 | 2026-06-30 | 109 days |
| 57 | Hy4 preview | tencent/hy4-preview | Tencent | 90.6 | — | 90.1 | 2026-08-28 | 50 days |
| 58 | GLM-5.1 | zhipuai/glm-5.1 | Zhipu AI | 90.5 | 95.4 | 83.3 | 2026-04-07 | 193 days |
| 59 | Kimi K2.6 | moonshotai/kimi-k2.6 | Moonshot AI | 90.3 | 95.0 | 83.3 | 2026-04-21 | 179 days |
| 60 | GPT-5.6 Terra | openai/gpt-5.6-terra | OpenAI | 90.3 | 94.5 | 84.0 | 2026-07-09 | 100 days |
| 61 | GLM-4.6V | zhipuai/glm-4.6v | Zhipu AI | 90.3 | 89.8 | — | 2025-12-08 | 313 days |
| 62 | Mistral Large 4 | mistral/mistral-large-4 | Mistral | 90.2 | 93.3 | 85.2 | 2026-10-06 | 11 days |
| 63 | DeepSeek V3 0324 | deepseek/deepseek-chat-v3-0324 | DeepSeek | 90.2 | 89.7 | — | 2025-03-24 | 572 days |
| 64 | DeepSeek V3 0324 | deepseek/deepseek-v3-0324 | DeepSeek | 90.2 | 89.7 | — | 2025-03-24 | 572 days |
| 65 | GPT-5 Mini | openai/gpt-5-mini | OpenAI | 90.1 | 89.6 | — | 2025-08-07 | 436 days |
| 66 | DeepSeek-R1 | deepseek/deepseek-r1 | DeepSeek | 90.1 | 89.6 | — | 2025-01-20 | 635 days |
| 67 | GPT-5.4 nano | openai/gpt-5.4-nano | OpenAI | 90.0 | 89.5 | — | 2026-03-17 | 214 days |
| 68 | MiMo-V2.5-Pro | xiaomi/mimo-v2.5-pro | Xiaomi | 89.9 | 95.6 | 81.7 | 2026-04-22 | 178 days |
| 69 | Mistral Medium 3 | mistral/mistral-medium-2505 | Mistral | 89.9 | 89.4 | — | 2025-05-07 | 528 days |
| 70 | GPT-6 Luna | openai/gpt-6-luna | OpenAI | 89.8 | 90.8 | 87.3 | 2026-09-22 | 25 days |
| 71 | Qwen3-Next 80B-A3B (Thinking) | alibaba/qwen3-next-80b-a3b-thinking | Alibaba | 89.8 | 89.3 | — | 2025-09 | 411 days |
| 72 | Qwen3 235B-A22B | alibaba/qwen3-235b-a22b | Alibaba | 89.7 | 89.2 | — | 2025-04 | 564 days |
| 73 | Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | Google | 89.6 | 96.6 | 79.9 | 2026-02-19 | 240 days |
| 74 | GPT-5.4 | openai/gpt-5.4 | OpenAI | 89.6 | 95.9 | 80.8 | 2026-03-05 | 226 days |
| 75 | Hy3 | tencent/hy3 | Tencent | 89.6 | 93.8 | 83.2 | 2026-07-06 | 103 days |
| 76 | GPT-5.6 Luna | openai/gpt-5.6-luna | OpenAI | 89.6 | 93.4 | 83.8 | 2026-07-09 | 100 days |
| 77 | GPT OSS 120B | openai/gpt-oss-120b | OpenAI | 89.6 | 89.1 | — | 2025-08-05 | 438 days |
| 78 | Claude Opus 4 | anthropic/claude-opus-4-20250514 | Anthropic | 89.6 | 89.1 | — | 2025-05-22 | 513 days |
| 79 | Gemini 3 Pro Preview | google/gemini-3-pro-preview | Google | 89.4 | 96.5 | 79.5 | 2025-11-18 | 333 days |
| 80 | Nova 2 Lite | amazon/nova-2-lite | Amazon | 89.4 | 88.9 | — | 2025-12-02 | 319 days |
| 81 | Nova 2 Lite | amazon/nova-2-lite-v1 | Amazon | 89.4 | 88.9 | — | 2025-12-02 | 319 days |
| 82 | Qwen3.6 Max Preview | alibaba/qwen3.6-max-preview | Alibaba | 89.3 | 94.4 | 81.8 | 2026-04-20 | 180 days |
| 83 | Claude Opus 4.5 | anthropic/claude-opus-4-5-20251101 | Anthropic | 89.1 | 94.7 | 81.1 | 2025-11-01 | 350 days |
| 84 | Gemma 3 27B IT | google/gemma-3-27b-it | Google | 89.1 | 88.6 | — | 2025-03-12 | 584 days |
| 85 | MiniMax-M3 | minimax/MiniMax-M3 | MiniMax | 88.8 | 93.5 | 81.8 | 2026-06-01 | 138 days |
| 86 | DeepSeek V4 Pro | deepseek/deepseek-v4-pro | DeepSeek | 88.6 | 94.7 | 79.9 | 2026-04-24 | 176 days |
| 87 | GLM-4.7-Flash | zhipuai/glm-4.7-flash | Zhipu AI | 88.6 | 88.1 | — | 2026-01-19 | 271 days |
| 88 | Qwen3.6 Plus | alibaba/qwen3.6-plus | Alibaba | 88.4 | 93.7 | 80.7 | 2026-04-02 | 198 days |
| 89 | GLM-5 | zhipuai/glm-5 | Zhipu AI | 88.1 | 94.4 | 79.2 | 2026-02-12 | 247 days |
| 90 | Kimi K2.5 | moonshotai/kimi-k2.5 | Moonshot AI | 88.1 | 94.3 | 79.3 | 2026-01 | 289 days |
| 91 | Claude Haiku 5.5 | anthropic/claude-haiku-5-5 | Anthropic | 88.0 | — | 87.5 | 2026-10-07 | 10 days |
| 92 | Qwen3 32B | alibaba/qwen3-32b | Alibaba | 88.0 | 87.5 | — | 2025-04 | 564 days |
| 93 | Trinity Large Preview | arcee-ai/trinity-large-preview | Arcee AI | 87.9 | 87.4 | — | 2026-01-27 | 263 days |
| 94 | Claude Sonnet 4 | anthropic/claude-sonnet-4-20250514 | Anthropic | 87.9 | 87.4 | — | 2025-05-22 | 513 days |
| 95 | Gemini 3.5 Flash Lite | google/gemini-3.5-flash-lite | Google | 87.8 | 93.6 | 79.5 | 2026-07-21 | 88 days |
| 96 | Mistral Small 3.2 | mistral/mistral-small-2506 | Mistral | 87.8 | 87.3 | — | 2025-06-20 | 484 days |
| 97 | MiMo-V2-Pro | xiaomi/mimo-v2-pro | Xiaomi | 87.7 | 93.7 | 79.1 | 2026-03-18 | 213 days |
| 98 | GLM-4.7 | zhipuai/glm-4.7 | Zhipu AI | 87.7 | 93.7 | 79.2 | 2025-12-22 | 299 days |
| 99 | o3-mini | openai/o3-mini | OpenAI | 87.7 | 87.2 | — | 2024-12-20 | 666 days |
| 100 | Gemma 3 12B IT | google/gemma-3-12b-it | Google | 87.6 | 87.1 | — | 2025-03-12 | 584 days |
| 101 | MiMo-V2.5 | xiaomi/mimo-v2.5 | Xiaomi | 87.5 | 93.2 | 79.4 | 2026-04-22 | 178 days |
| 102 | GLM-4.5V | zhipuai/glm-4.5v | Zhipu AI | 87.5 | 87.0 | — | 2025-08-11 | 432 days |
| 103 | DeepSeek-V3 | deepseek/deepseek-v3 | DeepSeek | 87.5 | 87.0 | — | 2024-12-26 | 660 days |
| 104 | Inkling | thinkingmachines/inkling | Thinking Machines | 87.4 | 94.1 | 78.0 | 2026-07-15 | 94 days |
| 105 | Command A | cohere/command-a-03-2025 | Cohere | 87.4 | 86.9 | — | 2025-03-13 | 583 days |
| 106 | QwQ 32B | alibaba/qwq-32b | Alibaba | 87.2 | 86.7 | — | 2025-03-05 | 591 days |
| 107 | GPT-5.1 | openai/gpt-5.1 | OpenAI | 87.0 | 94.2 | 77.0 | 2025-11-13 | 338 days |
| 108 | GLM-5V-Turbo | zhipuai/glm-5v-turbo | Zhipu AI | 86.9 | 93.8 | 77.4 | 2026-04-01 | 199 days |
| 109 | Qwen3.5 397B-A17B | alibaba/qwen3.5-397b-a17b | Alibaba | 86.9 | 93.8 | 77.3 | 2026-02-15 | 244 days |
| 110 | Claude Sonnet 4.5 | anthropic/claude-sonnet-4-5-20250929 | Anthropic | 86.6 | 93.9 | 76.5 | 2025-09-29 | 383 days |
| 111 | Granite 4.2 8B | ibm/granite-4.2-8b | IBM | 86.6 | 86.1 | — | 2026-08-31 | 47 days |
| 112 | GPT-5 Nano | openai/gpt-5-nano | OpenAI | 86.6 | 86.1 | — | 2025-08-07 | 436 days |
| 113 | GPT-5.2 | openai/gpt-5.2 | OpenAI | 86.5 | 92.4 | 78.2 | 2025-12-11 | 310 days |
| 114 | Qwen3 30B A3B | alibaba/qwen3-30b-a3b | Alibaba | 86.4 | 85.9 | — | 2025-04-28 | 537 days |
| 115 | Inkling Small | thinkingmachines/inkling-small | Thinking Machines | 86.2 | 92.2 | 77.8 | 2026-07-30 | 79 days |
| 116 | GPT-5 | openai/gpt-5 | OpenAI | 86.2 | 91.8 | 78.2 | 2025-08-07 | 436 days |
| 117 | Claude Opus 4.1 | anthropic/claude-opus-4-1-20250805 | Anthropic | 86.0 | 92.6 | 76.7 | 2025-08-05 | 438 days |
| 118 | GPT-5.4 mini | openai/gpt-5.4-mini | OpenAI | 85.9 | 92.1 | 77.2 | 2026-03-17 | 214 days |
| 119 | MiniMax-M2.7 | minimax/MiniMax-M2.7 | MiniMax | 85.7 | 91.7 | 77.2 | 2026-03-18 | 213 days |
| 120 | GLM-4.6 | zhipuai/glm-4.6 | Zhipu AI | 85.5 | 94.0 | 74.0 | 2025-09-30 | 382 days |
| 121 | DeepSeek V3.2 | deepseek/deepseek-v3.2 | DeepSeek | 85.5 | 93.0 | 75.2 | 2025-12-01 | 320 days |
| 122 | GPT-4o (2024-05-13) | openai/gpt-4o-2024-05-13 | OpenAI | 85.4 | 84.9 | — | 2024-05-13 | 887 days |
| 123 | Claude Sonnet 3.7 | anthropic/claude-3-7-sonnet-20250219 | Anthropic | 85.3 | 84.8 | — | 2025-02-19 | 605 days |
| 124 | Qwen3.5 122B-A10B | alibaba/qwen3.5-122b-a10b | Alibaba | 85.2 | 92.5 | 75.1 | 2026-02-23 | 236 days |
| 125 | Claude Sonnet 3.5 v2 | anthropic/claude-3-5-sonnet-20241022 | Anthropic | 85.2 | 84.7 | — | 2024-10-22 | 725 days |
| 126 | Qwen3.5 27B | alibaba/qwen3.5-27b | Alibaba | 84.8 | 91.9 | 75.0 | 2026-02-23 | 236 days |
| 127 | Gemma 3 4B IT | google/gemma-3-4b-it | Google | 84.7 | 84.2 | — | 2025-03-12 | 584 days |
| 128 | GPT OSS 20B | openai/gpt-oss-20b | OpenAI | 84.5 | 84.0 | — | 2025-08-05 | 438 days |
| 129 | Grok 4.3 | xai/grok-4.3 | xAI | 84.4 | 91.2 | 74.9 | 2026-04-17 | 183 days |
| 130 | Solar Pro 4 | upstage/solar-pro4 | Upstage | 84.4 | 90.5 | 75.7 | 2026-08-06 | 72 days |
| 131 | MiMo-V2-Flash | xiaomi/mimo-v2-flash | Xiaomi | 84.2 | 92.1 | 73.4 | 2025-12-16 | 305 days |
| 132 | Llama 3.1 Nemotron 70B Instruct | nvidia/llama-3.1-nemotron-70b-instruct | NVIDIA | 84.2 | 83.7 | — | 2025-04-15 | 550 days |
| 133 | GPT-4o (2024-08-06) | openai/gpt-4o-2024-08-06 | OpenAI | 84.2 | 83.7 | — | 2024-08-06 | 802 days |
| 134 | Kimi K2 Thinking Turbo | moonshotai/kimi-k2-thinking-turbo | Moonshot AI | 84.1 | 92.3 | 73.0 | 2025-11-06 | 345 days |
| 135 | Mistral Small 3.1 24B | mistral/mistral-small-3-1-24b-instruct-2503 | Mistral | 83.8 | 83.3 | — | 2025-03-17 | 579 days |
| 136 | MiniMax-M2.5 | minimax/MiniMax-M2.5 | MiniMax | 83.7 | 88.7 | 76.5 | 2026-02-12 | 247 days |
| 137 | Llama-3.3-70B-Instruct | meta/llama-3.3-70b-instruct | Meta | 83.7 | 83.2 | — | 2024-12-06 | 680 days |
| 138 | Claude Haiku 4.5 | anthropic/claude-haiku-4-5-20251001 | Anthropic | 83.6 | 91.1 | 73.4 | 2025-10-15 | 367 days |
| 139 | Gemini 2.5 Pro | google/gemini-2.5-pro | Google | 83.3 | 95.1 | 67.7 | 2025-06-17 | 487 days |
| 140 | Mistral Large 2407 | mistral/mistral-large-2407 | Mistral | 83.1 | 82.6 | — | 2024-11-19 | 697 days |
| 141 | Mistral Large 2.1 | mistral/mistral-large-2411 | Mistral | 83.1 | 82.6 | — | 2024-11-18 | 698 days |
| 142 | Mistral Medium 3.5 | mistral/mistral-medium-3-5 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-30 | 170 days |
| 143 | Mistral Medium 3.5 | mistral/mistral-medium-2604 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-29 | 171 days |
| 144 | Llama-3.1-70B-Instruct | meta/llama-3.1-70b-instruct | Meta | 82.8 | 82.3 | — | 2024-07-23 | 816 days |
| 145 | Gemini 3.1 Flash Lite Preview | google/gemini-3.1-flash-lite-preview | Google | 82.5 | 92.4 | 69.4 | 2026-03-03 | 228 days |
| 146 | Claude Haiku 3.5 | anthropic/claude-3-5-haiku-20241022 | Anthropic | 82.4 | 81.9 | — | 2024-10-22 | 725 days |
| 147 | Mistral Large 3 | mistral/mistral-large-2512 | Mistral | 82.3 | 93.2 | 67.9 | 2025-12-02 | 319 days |
| 148 | Grok 4.1 Fast | xai/grok-4.1-fast | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 149 | Grok 4.1 Fast (Reasoning) | xai/grok-4.1-fast-reasoning | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 150 | Kimi K2.7 Code | moonshotai/kimi-k2.7-code | Moonshot AI | 81.9 | — | 81.4 | 2026-06-12 | 127 days |
| 151 | Qwen3.5 35B-A3B | alibaba/qwen3.5-35b-a3b | Alibaba | 81.7 | 91.0 | 69.2 | 2026-02-23 | 236 days |
| 152 | Qwen3.5 Flash | alibaba/qwen3.5-flash | Alibaba | 81.6 | 91.2 | 68.7 | 2026-02-23 | 236 days |
| 153 | Mistral Small 3 | mistral/mistral-small-24b-instruct-2501 | Mistral | 81.0 | 80.5 | — | 2025-01-30 | 625 days |
| 154 | Gemma 2 27B | google/gemma-2-27b-it | Google | 80.9 | 80.4 | — | 2024-07-13 | 826 days |
| 155 | Qwen3-Coder 480B-A35B Instruct | alibaba/qwen3-coder-480b-a35b-instruct | Alibaba | 80.8 | 88.5 | 70.4 | 2025-04 | 564 days |
| 156 | MiniMax-M2 | minimax/MiniMax-M2 | MiniMax | 80.8 | 87.4 | 71.6 | 2025-10-27 | 355 days |
| 157 | Qwen2.5-Coder-32B-Instruct | alibaba/qwen2.5-coder-32b-instruct | Alibaba | 80.8 | 80.3 | — | 2024-11-12 | 704 days |
| 158 | Command R+ | cohere/command-r-plus-08-2024 | Cohere | 80.7 | 80.2 | — | 2024-08-30 | 778 days |
| 159 | Aya Expanse 32B | cohere/c4ai-aya-expanse-32b | Cohere | 80.4 | 79.9 | — | 2024-10-24 | 723 days |
| 160 | X-Ai/Grok-4-Fast-Reasoning | xai/grok-4-fast-reasoning | xAI | 79.5 | 91.3 | 64.0 | 2025-12-18 | 303 days |
| 161 | Trinity Large Thinking | arcee-ai/trinity-large-thinking | Arcee AI | 79.3 | 87.5 | 68.3 | 2026-04-01 | 199 days |
| 162 | Claude Haiku 3 | anthropic/claude-3-haiku-20240307 | Anthropic | 78.5 | 78.0 | — | 2024-03-13 | 948 days |
| 163 | Mercury 2 | inception/mercury-2 | Inception | 78.2 | 88.4 | 64.6 | 2026-03-04 | 227 days |
| 164 | GPT-5.3 Codex | openai/gpt-5.3-codex | OpenAI | 78.1 | — | 77.6 | 2026-02-05 | 254 days |
| 165 | Command R | cohere/command-r-08-2024 | Cohere | 78.0 | 77.5 | — | 2024-08-30 | 778 days |
| 166 | Llama-3.1-8B-Instruct | meta/llama-3.1-8b-instruct | Meta | 77.9 | 77.4 | — | 2024-07-23 | 816 days |
| 167 | Aya Expanse 8B | cohere/c4ai-aya-expanse-8b | Cohere | 77.8 | 77.3 | — | 2024-10-24 | 723 days |
| 168 | Laguna M.1 | poolside/laguna-m.1 | Poolside | 75.0 | — | 74.5 | 2026-04-28 | 172 days |
| 169 | GPT-5.2 Codex | openai/gpt-5.2-codex | OpenAI | 74.3 | — | 73.9 | 2025-12-11 | 310 days |
| 170 | GPT-5.1 Codex | openai/gpt-5.1-codex | OpenAI | 74.2 | — | 73.8 | 2025-11-13 | 338 days |
| 171 | GPT-5.1 Codex Max | openai/gpt-5.1-codex-max | OpenAI | 74.2 | — | 73.8 | 2025-11-13 | 338 days |
| 172 | Laguna XS.2 | poolside/laguna-xs.2 | Poolside | 72.3 | — | 71.9 | 2026-04-28 | 172 days |
| 173 | Llama 3.2 1B Instruct | meta/llama-3.2-1b-instruct | Meta | 69.2 | 68.8 | — | 2024-09-25 | 752 days |
| 174 | GPT-5.1 Codex mini | openai/gpt-5.1-codex-mini | OpenAI | 69.1 | — | 68.7 | 2025-11-13 | 338 days |
| 175 | Devstral 2 | mistral/devstral-2512 | Mistral | 66.4 | — | 66.0 | 2025-12-09 | 312 days |
| 176 | x-AI/Grok-Code-Fast 1 | xai/grok-code-fast-1 | xAI | 64.8 | — | 64.4 | 2025-09-02 | 410 days |
| 177 | Devstral Medium | mistral/devstral-medium-2507 | Mistral | 59.5 | — | 59.1 | 2025-07-10 | 464 days |

## Intelligence

Reasoning, knowledge, and scientific ability

163 models

| Rank | Model | Model ID | Lab | Overall | Intelligence | Coding | Released | Age |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Gemini 4 Argon | google/gemini-4-argon | Google | 97.3 | 100.0 | 92.6 | 2026-10-13 | 4 days |
| 2 | Claude Opus 5.5 | anthropic/claude-opus-5-5 | Anthropic | 100.0 | 98.9 | 100.0 | 2026-09-22 | 25 days |
| 3 | Claude Fable 5.1 | anthropic/claude-fable-5-1 | Anthropic | 98.1 | 98.6 | 96.2 | 2026-09-01 | 46 days |
| 4 | Claude Opus 5 | anthropic/claude-opus-5 | Anthropic | 96.7 | 98.4 | 93.3 | 2026-07-24 | 85 days |
| 5 | Muse Wonder | meta/muse-wonder-1.0 | Meta | 95.5 | 98.0 | 91.2 | 2026-10-12 | 5 days |
| 6 | Claude Opus 4.6 | anthropic/claude-opus-4-6 | Anthropic | 92.9 | 98.0 | 85.4 | 2026-02-05 | 254 days |
| 7 | Gemini 3.8 Flash | google/gemini-3.8-flash | Google | 93.7 | 97.8 | 87.5 | 2026-09-02 | 45 days |
| 8 | MiMo-V2.6-Pro | xiaomi/mimo-v2.6-pro | Xiaomi | 94.5 | 97.3 | 89.7 | 2026-09-22 | 25 days |
| 9 | Claude Fable 5 | anthropic/claude-fable-5 | Anthropic | 94.5 | 97.3 | 89.7 | 2026-06-09 | 130 days |
| 10 | Muse Spark 1.3 | meta/muse-spark-1.3 | Meta | 95.3 | 97.2 | 91.6 | 2026-09-02 | 45 days |
| 11 | Claude Opus 4.7 | anthropic/claude-opus-4-7 | Anthropic | 92.7 | 97.2 | 86.0 | 2026-04-16 | 184 days |
| 12 | Gemini 3.7 Flash | google/gemini-3.7-flash | Google | 93.5 | 97.1 | 87.8 | 2026-08-13 | 65 days |
| 13 | Qwen3.8 Max 0902 | alibaba/qwen3.8-max-0902 | Alibaba | 95.4 | 96.8 | 92.4 | 2026-09-02 | 45 days |
| 14 | Muse Spark 1.2 | meta/muse-spark-1.2 | Meta | 91.9 | 96.8 | 84.7 | 2026-08-05 | 73 days |
| 15 | Qwen3.8 Max | alibaba/qwen3.8-max | Alibaba | 95.4 | 96.8 | 92.3 | 2026-08-03 | 75 days |
| 16 | Gemini 3.5 Flash | google/gemini-3.5-flash | Google | 91.0 | 96.7 | 82.8 | 2026-05-19 | 151 days |
| 17 | Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | Google | 89.6 | 96.6 | 79.9 | 2026-02-19 | 240 days |
| 18 | Gemini 3.6 Flash | google/gemini-3.6-flash | Google | 91.8 | 96.5 | 84.9 | 2026-07-21 | 88 days |
| 19 | Muse Spark 1.1 | meta/muse-spark-1.1 | Meta | 92.0 | 96.5 | 85.2 | 2026-04-08 | 192 days |
| 20 | Gemini 3 Pro Preview | google/gemini-3-pro-preview | Google | 89.4 | 96.5 | 79.5 | 2025-11-18 | 333 days |
| 21 | Kimi K3 | moonshotai/kimi-k3 | Moonshot AI | 94.6 | 96.2 | 91.4 | 2026-07-16 | 93 days |
| 22 | Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | Anthropic | 97.4 | 96.0 | 97.9 | 2026-09-28 | 19 days |
| 23 | GLM-5.3-Flash | zhipuai/glm-5.3-flash | Zhipu AI | 93.3 | 96.0 | 88.7 | 2026-08-26 | 52 days |
| 24 | GLM-5.3 | zhipuai/glm-5.3 | Zhipu AI | 93.6 | 96.0 | 89.5 | 2026-08-14 | 64 days |
| 25 | GLM-5.2 | zhipuai/glm-5.2 | Zhipu AI | 93.2 | 96.0 | 88.6 | 2026-06-13 | 126 days |
| 26 | GPT-5.5 | openai/gpt-5.5 | OpenAI | 90.9 | 96.0 | 83.5 | 2026-04-23 | 177 days |
| 27 | GPT-5.4 | openai/gpt-5.4 | OpenAI | 89.6 | 95.9 | 80.8 | 2026-03-05 | 226 days |
| 28 | MiMo-V2.5-Pro | xiaomi/mimo-v2.5-pro | Xiaomi | 89.9 | 95.6 | 81.7 | 2026-04-22 | 178 days |
| 29 | DeepSeek V4.1 Flash | deepseek/deepseek-v4.1-flash | DeepSeek | 93.3 | 95.5 | 89.4 | 2026-09-10 | 37 days |
| 30 | GLM-5.1 | zhipuai/glm-5.1 | Zhipu AI | 90.5 | 95.4 | 83.3 | 2026-04-07 | 193 days |
| 31 | Claude Opus 4.8 | anthropic/claude-opus-4-8 | Anthropic | 91.6 | 95.3 | 85.9 | 2026-05-28 | 142 days |
| 32 | GPT-5.6 Sol | openai/gpt-5.6-sol | OpenAI | 93.1 | 95.1 | 89.3 | 2026-07-09 | 100 days |
| 33 | Claude Sonnet 4.6 | anthropic/claude-sonnet-4-6 | Anthropic | 90.7 | 95.1 | 84.1 | 2026-02-17 | 242 days |
| 34 | Gemini 2.5 Pro | google/gemini-2.5-pro | Google | 83.3 | 95.1 | 67.7 | 2025-06-17 | 487 days |
| 35 | MiMo-V2.6-Flash | xiaomi/mimo-v2.6-flash | Xiaomi | 93.5 | 95.0 | 90.3 | 2026-09-22 | 25 days |
| 36 | Kimi K2.6 | moonshotai/kimi-k2.6 | Moonshot AI | 90.3 | 95.0 | 83.3 | 2026-04-21 | 179 days |
| 37 | Qwen3.7 Plus | alibaba/qwen3.7-plus | Alibaba | 95.5 | 94.9 | — | 2026-06-02 | 137 days |
| 38 | DeepSeek V4 Pro | deepseek/deepseek-v4-pro | DeepSeek | 88.6 | 94.7 | 79.9 | 2026-04-24 | 176 days |
| 39 | Claude Opus 4.5 | anthropic/claude-opus-4-5-20251101 | Anthropic | 89.1 | 94.7 | 81.1 | 2025-11-01 | 350 days |
| 40 | GPT-6.1 Sol | openai/gpt-6.1-sol | OpenAI | 96.3 | 94.5 | 97.2 | 2026-09-29 | 18 days |
| 41 | GPT-5.6 Terra | openai/gpt-5.6-terra | OpenAI | 90.3 | 94.5 | 84.0 | 2026-07-09 | 100 days |
| 42 | Grok 4.5 | xai/grok-4.5 | xAI | 91.1 | 94.5 | 85.7 | 2026-07-08 | 101 days |
| 43 | Qwen3.6 Max Preview | alibaba/qwen3.6-max-preview | Alibaba | 89.3 | 94.4 | 81.8 | 2026-04-20 | 180 days |
| 44 | GLM-5 | zhipuai/glm-5 | Zhipu AI | 88.1 | 94.4 | 79.2 | 2026-02-12 | 247 days |
| 45 | Kimi K2.5 | moonshotai/kimi-k2.5 | Moonshot AI | 88.1 | 94.3 | 79.3 | 2026-01 | 289 days |
| 46 | GPT-5.1 | openai/gpt-5.1 | OpenAI | 87.0 | 94.2 | 77.0 | 2025-11-13 | 338 days |
| 47 | GPT-6 Astra | openai/gpt-6-astra | OpenAI | 96.6 | 94.1 | 98.3 | 2026-09-04 | 43 days |
| 48 | Step 5 Preview | stepfun/step-5-preview | StepFun | 91.1 | 94.1 | 86.3 | 2026-09-16 | 31 days |
| 49 | Inkling | thinkingmachines/inkling | Thinking Machines | 87.4 | 94.1 | 78.0 | 2026-07-15 | 94 days |
| 50 | Claude Sonnet 5 | anthropic/claude-sonnet-5 | Anthropic | 90.6 | 94.1 | 85.0 | 2026-06-30 | 109 days |
| 51 | Qwen3.8 27B | alibaba/qwen3.8-27b | Alibaba | 91.9 | 94.0 | 88.0 | 2026-08-14 | 64 days |
| 52 | GLM-4.6 | zhipuai/glm-4.6 | Zhipu AI | 85.5 | 94.0 | 74.0 | 2025-09-30 | 382 days |
| 53 | Qwen3 Max Preview | alibaba/qwen3-max-preview | Alibaba | 94.5 | 93.9 | — | 2025-09-05 | 407 days |
| 54 | Claude Sonnet 4.5 | anthropic/claude-sonnet-4-5-20250929 | Anthropic | 86.6 | 93.9 | 76.5 | 2025-09-29 | 383 days |
| 55 | Hy3 | tencent/hy3 | Tencent | 89.6 | 93.8 | 83.2 | 2026-07-06 | 103 days |
| 56 | GLM-5V-Turbo | zhipuai/glm-5v-turbo | Zhipu AI | 86.9 | 93.8 | 77.4 | 2026-04-01 | 199 days |
| 57 | Qwen3.5 397B-A17B | alibaba/qwen3.5-397b-a17b | Alibaba | 86.9 | 93.8 | 77.3 | 2026-02-15 | 244 days |
| 58 | Qwen3.6 Plus | alibaba/qwen3.6-plus | Alibaba | 88.4 | 93.7 | 80.7 | 2026-04-02 | 198 days |
| 59 | MiMo-V2-Pro | xiaomi/mimo-v2-pro | Xiaomi | 87.7 | 93.7 | 79.1 | 2026-03-18 | 213 days |
| 60 | GLM-4.7 | zhipuai/glm-4.7 | Zhipu AI | 87.7 | 93.7 | 79.2 | 2025-12-22 | 299 days |
| 61 | Gemini 3.5 Flash Lite | google/gemini-3.5-flash-lite | Google | 87.8 | 93.6 | 79.5 | 2026-07-21 | 88 days |
| 62 | MiniMax-M3 | minimax/MiniMax-M3 | MiniMax | 88.8 | 93.5 | 81.8 | 2026-06-01 | 138 days |
| 63 | GPT-5.6 Luna | openai/gpt-5.6-luna | OpenAI | 89.6 | 93.4 | 83.8 | 2026-07-09 | 100 days |
| 64 | DeepSeek V4 Flash | deepseek/deepseek-v4-flash | DeepSeek | 91.2 | 93.4 | 87.3 | 2026-04-24 | 176 days |
| 65 | GLM-4.5 | zhipuai/glm-4.5 | Zhipu AI | 93.9 | 93.3 | — | 2025-07-28 | 446 days |
| 66 | Mistral Large 4 | mistral/mistral-large-4 | Mistral | 90.2 | 93.3 | 85.2 | 2026-10-06 | 11 days |
| 67 | DeepSeek R1 0528 | deepseek/deepseek-r1-0528 | DeepSeek | 93.8 | 93.2 | — | 2025-05-28 | 507 days |
| 68 | Grok 4.6 | xai/grok-4.6 | xAI | 92.0 | 93.2 | 89.3 | 2026-08-12 | 66 days |
| 69 | MiMo-V2.5 | xiaomi/mimo-v2.5 | Xiaomi | 87.5 | 93.2 | 79.4 | 2026-04-22 | 178 days |
| 70 | Mistral Large 3 | mistral/mistral-large-2512 | Mistral | 82.3 | 93.2 | 67.9 | 2025-12-02 | 319 days |
| 71 | DeepSeek V3.2 | deepseek/deepseek-v3.2 | DeepSeek | 85.5 | 93.0 | 75.2 | 2025-12-01 | 320 days |
| 72 | MiMo-V2-Omni | xiaomi/mimo-v2-omni | Xiaomi | 93.5 | 92.9 | — | 2026-03-18 | 213 days |
| 73 | Qwen3 VL 235B A22B Instruct | alibaba/qwen3-vl-235b-a22b-instruct | Alibaba | 93.3 | 92.7 | — | 2025-09-23 | 389 days |
| 74 | Mistral Medium 3.5 | mistral/mistral-medium-3-5 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-30 | 170 days |
| 75 | Mistral Medium 3.5 | mistral/mistral-medium-2604 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-29 | 171 days |
| 76 | GPT-5.5 Instant | openai/gpt-5.5-instant | OpenAI | 93.2 | 92.6 | — | 2026-05-05 | 165 days |
| 77 | DeepSeek V3.1 | deepseek/deepseek-chat-v3.1 | DeepSeek | 93.2 | 92.6 | — | 2025-08-21 | 422 days |
| 78 | DeepSeek-V3.1 | deepseek/deepseek-v3.1 | DeepSeek | 93.2 | 92.6 | — | 2025-08-21 | 422 days |
| 79 | Qwen3 235B-A22B Instruct 2507 | alibaba/qwen3-235b-a22b-instruct-2507 | Alibaba | 93.2 | 92.6 | — | 2025-07-21 | 453 days |
| 80 | Claude Opus 4.1 | anthropic/claude-opus-4-1-20250805 | Anthropic | 86.0 | 92.6 | 76.7 | 2025-08-05 | 438 days |
| 81 | Qwen3-Next 80B-A3B Instruct | alibaba/qwen3-next-80b-a3b-instruct | Alibaba | 93.1 | 92.5 | — | 2025-09 | 411 days |
| 82 | Gemini 2.5 Flash | google/gemini-2.5-flash | Google | 93.1 | 92.5 | — | 2025-06-17 | 487 days |
| 83 | Qwen3.5 122B-A10B | alibaba/qwen3.5-122b-a10b | Alibaba | 85.2 | 92.5 | 75.1 | 2026-02-23 | 236 days |
| 84 | Gemini 3.1 Flash Lite Preview | google/gemini-3.1-flash-lite-preview | Google | 82.5 | 92.4 | 69.4 | 2026-03-03 | 228 days |
| 85 | GPT-5.2 | openai/gpt-5.2 | OpenAI | 86.5 | 92.4 | 78.2 | 2025-12-11 | 310 days |
| 86 | Kimi K2 Thinking Turbo | moonshotai/kimi-k2-thinking-turbo | Moonshot AI | 84.1 | 92.3 | 73.0 | 2025-11-06 | 345 days |
| 87 | Inkling Small | thinkingmachines/inkling-small | Thinking Machines | 86.2 | 92.2 | 77.8 | 2026-07-30 | 79 days |
| 88 | GPT-5.4 mini | openai/gpt-5.4-mini | OpenAI | 85.9 | 92.1 | 77.2 | 2026-03-17 | 214 days |
| 89 | MiMo-V2-Flash | xiaomi/mimo-v2-flash | Xiaomi | 84.2 | 92.1 | 73.4 | 2025-12-16 | 305 days |
| 90 | Qwen3.5 27B | alibaba/qwen3.5-27b | Alibaba | 84.8 | 91.9 | 75.0 | 2026-02-23 | 236 days |
| 91 | Grok 4.1 Fast | xai/grok-4.1-fast | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 92 | Grok 4.1 Fast (Reasoning) | xai/grok-4.1-fast-reasoning | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 93 | GPT-5 | openai/gpt-5 | OpenAI | 86.2 | 91.8 | 78.2 | 2025-08-07 | 436 days |
| 94 | MiniMax-M2.7 | minimax/MiniMax-M2.7 | MiniMax | 85.7 | 91.7 | 77.2 | 2026-03-18 | 213 days |
| 95 | Step 3.5 Flash | stepfun/step-3.5-flash | StepFun | 92.1 | 91.5 | — | 2026-01-29 | 261 days |
| 96 | Qwen3 VL 235B A22B Thinking | alibaba/qwen3-vl-235b-a22b-thinking | Alibaba | 92.0 | 91.4 | — | 2025-09-23 | 389 days |
| 97 | Grok 4.7 | xai/grok-4.7 | xAI | 91.6 | 91.4 | 90.6 | 2026-09-21 | 26 days |
| 98 | X-Ai/Grok-4-Fast-Reasoning | xai/grok-4-fast-reasoning | xAI | 79.5 | 91.3 | 64.0 | 2025-12-18 | 303 days |
| 99 | GPT-6 Sol | openai/gpt-6-sol | OpenAI | 92.6 | 91.2 | 93.1 | 2026-09-22 | 25 days |
| 100 | Grok 4.3 | xai/grok-4.3 | xAI | 84.4 | 91.2 | 74.9 | 2026-04-17 | 183 days |
| 101 | Qwen3.5 Flash | alibaba/qwen3.5-flash | Alibaba | 81.6 | 91.2 | 68.7 | 2026-02-23 | 236 days |
| 102 | Claude Haiku 4.5 | anthropic/claude-haiku-4-5-20251001 | Anthropic | 83.6 | 91.1 | 73.4 | 2025-10-15 | 367 days |
| 103 | Qwen3.5 35B-A3B | alibaba/qwen3.5-35b-a3b | Alibaba | 81.7 | 91.0 | 69.2 | 2026-02-23 | 236 days |
| 104 | GPT-6 Luna | openai/gpt-6-luna | OpenAI | 89.8 | 90.8 | 87.3 | 2026-09-22 | 25 days |
| 105 | GPT-5.3 Chat (latest) | openai/gpt-5.3-chat-latest | OpenAI | 91.2 | 90.6 | — | 2026-03-03 | 228 days |
| 106 | Solar Pro 4 | upstage/solar-pro4 | Upstage | 84.4 | 90.5 | 75.7 | 2026-08-06 | 72 days |
| 107 | GLM-4.5-Air | zhipuai/glm-4.5-air | Zhipu AI | 90.8 | 90.3 | — | 2025-07-28 | 446 days |
| 108 | GLM-4.6V | zhipuai/glm-4.6v | Zhipu AI | 90.3 | 89.8 | — | 2025-12-08 | 313 days |
| 109 | DeepSeek V3 0324 | deepseek/deepseek-chat-v3-0324 | DeepSeek | 90.2 | 89.7 | — | 2025-03-24 | 572 days |
| 110 | DeepSeek V3 0324 | deepseek/deepseek-v3-0324 | DeepSeek | 90.2 | 89.7 | — | 2025-03-24 | 572 days |
| 111 | GPT-5 Mini | openai/gpt-5-mini | OpenAI | 90.1 | 89.6 | — | 2025-08-07 | 436 days |
| 112 | DeepSeek-R1 | deepseek/deepseek-r1 | DeepSeek | 90.1 | 89.6 | — | 2025-01-20 | 635 days |
| 113 | GPT-5.4 nano | openai/gpt-5.4-nano | OpenAI | 90.0 | 89.5 | — | 2026-03-17 | 214 days |
| 114 | Mistral Medium 3 | mistral/mistral-medium-2505 | Mistral | 89.9 | 89.4 | — | 2025-05-07 | 528 days |
| 115 | Qwen3-Next 80B-A3B (Thinking) | alibaba/qwen3-next-80b-a3b-thinking | Alibaba | 89.8 | 89.3 | — | 2025-09 | 411 days |
| 116 | Qwen3 235B-A22B | alibaba/qwen3-235b-a22b | Alibaba | 89.7 | 89.2 | — | 2025-04 | 564 days |
| 117 | GPT OSS 120B | openai/gpt-oss-120b | OpenAI | 89.6 | 89.1 | — | 2025-08-05 | 438 days |
| 118 | Claude Opus 4 | anthropic/claude-opus-4-20250514 | Anthropic | 89.6 | 89.1 | — | 2025-05-22 | 513 days |
| 119 | Nova 2 Lite | amazon/nova-2-lite | Amazon | 89.4 | 88.9 | — | 2025-12-02 | 319 days |
| 120 | Nova 2 Lite | amazon/nova-2-lite-v1 | Amazon | 89.4 | 88.9 | — | 2025-12-02 | 319 days |
| 121 | MiniMax-M2.5 | minimax/MiniMax-M2.5 | MiniMax | 83.7 | 88.7 | 76.5 | 2026-02-12 | 247 days |
| 122 | Gemma 3 27B IT | google/gemma-3-27b-it | Google | 89.1 | 88.6 | — | 2025-03-12 | 584 days |
| 123 | Qwen3-Coder 480B-A35B Instruct | alibaba/qwen3-coder-480b-a35b-instruct | Alibaba | 80.8 | 88.5 | 70.4 | 2025-04 | 564 days |
| 124 | Mercury 2 | inception/mercury-2 | Inception | 78.2 | 88.4 | 64.6 | 2026-03-04 | 227 days |
| 125 | GLM-4.7-Flash | zhipuai/glm-4.7-flash | Zhipu AI | 88.6 | 88.1 | — | 2026-01-19 | 271 days |
| 126 | Qwen3 32B | alibaba/qwen3-32b | Alibaba | 88.0 | 87.5 | — | 2025-04 | 564 days |
| 127 | Trinity Large Thinking | arcee-ai/trinity-large-thinking | Arcee AI | 79.3 | 87.5 | 68.3 | 2026-04-01 | 199 days |
| 128 | Trinity Large Preview | arcee-ai/trinity-large-preview | Arcee AI | 87.9 | 87.4 | — | 2026-01-27 | 263 days |
| 129 | Claude Sonnet 4 | anthropic/claude-sonnet-4-20250514 | Anthropic | 87.9 | 87.4 | — | 2025-05-22 | 513 days |
| 130 | MiniMax-M2 | minimax/MiniMax-M2 | MiniMax | 80.8 | 87.4 | 71.6 | 2025-10-27 | 355 days |
| 131 | Mistral Small 3.2 | mistral/mistral-small-2506 | Mistral | 87.8 | 87.3 | — | 2025-06-20 | 484 days |
| 132 | o3-mini | openai/o3-mini | OpenAI | 87.7 | 87.2 | — | 2024-12-20 | 666 days |
| 133 | Gemma 3 12B IT | google/gemma-3-12b-it | Google | 87.6 | 87.1 | — | 2025-03-12 | 584 days |
| 134 | GLM-4.5V | zhipuai/glm-4.5v | Zhipu AI | 87.5 | 87.0 | — | 2025-08-11 | 432 days |
| 135 | DeepSeek-V3 | deepseek/deepseek-v3 | DeepSeek | 87.5 | 87.0 | — | 2024-12-26 | 660 days |
| 136 | Command A | cohere/command-a-03-2025 | Cohere | 87.4 | 86.9 | — | 2025-03-13 | 583 days |
| 137 | QwQ 32B | alibaba/qwq-32b | Alibaba | 87.2 | 86.7 | — | 2025-03-05 | 591 days |
| 138 | Granite 4.2 8B | ibm/granite-4.2-8b | IBM | 86.6 | 86.1 | — | 2026-08-31 | 47 days |
| 139 | GPT-5 Nano | openai/gpt-5-nano | OpenAI | 86.6 | 86.1 | — | 2025-08-07 | 436 days |
| 140 | Qwen3 30B A3B | alibaba/qwen3-30b-a3b | Alibaba | 86.4 | 85.9 | — | 2025-04-28 | 537 days |
| 141 | GPT-4o (2024-05-13) | openai/gpt-4o-2024-05-13 | OpenAI | 85.4 | 84.9 | — | 2024-05-13 | 887 days |
| 142 | Claude Sonnet 3.7 | anthropic/claude-3-7-sonnet-20250219 | Anthropic | 85.3 | 84.8 | — | 2025-02-19 | 605 days |
| 143 | Claude Sonnet 3.5 v2 | anthropic/claude-3-5-sonnet-20241022 | Anthropic | 85.2 | 84.7 | — | 2024-10-22 | 725 days |
| 144 | Gemma 3 4B IT | google/gemma-3-4b-it | Google | 84.7 | 84.2 | — | 2025-03-12 | 584 days |
| 145 | GPT OSS 20B | openai/gpt-oss-20b | OpenAI | 84.5 | 84.0 | — | 2025-08-05 | 438 days |
| 146 | Llama 3.1 Nemotron 70B Instruct | nvidia/llama-3.1-nemotron-70b-instruct | NVIDIA | 84.2 | 83.7 | — | 2025-04-15 | 550 days |
| 147 | GPT-4o (2024-08-06) | openai/gpt-4o-2024-08-06 | OpenAI | 84.2 | 83.7 | — | 2024-08-06 | 802 days |
| 148 | Mistral Small 3.1 24B | mistral/mistral-small-3-1-24b-instruct-2503 | Mistral | 83.8 | 83.3 | — | 2025-03-17 | 579 days |
| 149 | Llama-3.3-70B-Instruct | meta/llama-3.3-70b-instruct | Meta | 83.7 | 83.2 | — | 2024-12-06 | 680 days |
| 150 | Mistral Large 2407 | mistral/mistral-large-2407 | Mistral | 83.1 | 82.6 | — | 2024-11-19 | 697 days |
| 151 | Mistral Large 2.1 | mistral/mistral-large-2411 | Mistral | 83.1 | 82.6 | — | 2024-11-18 | 698 days |
| 152 | Llama-3.1-70B-Instruct | meta/llama-3.1-70b-instruct | Meta | 82.8 | 82.3 | — | 2024-07-23 | 816 days |
| 153 | Claude Haiku 3.5 | anthropic/claude-3-5-haiku-20241022 | Anthropic | 82.4 | 81.9 | — | 2024-10-22 | 725 days |
| 154 | Mistral Small 3 | mistral/mistral-small-24b-instruct-2501 | Mistral | 81.0 | 80.5 | — | 2025-01-30 | 625 days |
| 155 | Gemma 2 27B | google/gemma-2-27b-it | Google | 80.9 | 80.4 | — | 2024-07-13 | 826 days |
| 156 | Qwen2.5-Coder-32B-Instruct | alibaba/qwen2.5-coder-32b-instruct | Alibaba | 80.8 | 80.3 | — | 2024-11-12 | 704 days |
| 157 | Command R+ | cohere/command-r-plus-08-2024 | Cohere | 80.7 | 80.2 | — | 2024-08-30 | 778 days |
| 158 | Aya Expanse 32B | cohere/c4ai-aya-expanse-32b | Cohere | 80.4 | 79.9 | — | 2024-10-24 | 723 days |
| 159 | Claude Haiku 3 | anthropic/claude-3-haiku-20240307 | Anthropic | 78.5 | 78.0 | — | 2024-03-13 | 948 days |
| 160 | Command R | cohere/command-r-08-2024 | Cohere | 78.0 | 77.5 | — | 2024-08-30 | 778 days |
| 161 | Llama-3.1-8B-Instruct | meta/llama-3.1-8b-instruct | Meta | 77.9 | 77.4 | — | 2024-07-23 | 816 days |
| 162 | Aya Expanse 8B | cohere/c4ai-aya-expanse-8b | Cohere | 77.8 | 77.3 | — | 2024-10-24 | 723 days |
| 163 | Llama 3.2 1B Instruct | meta/llama-3.2-1b-instruct | Meta | 69.2 | 68.8 | — | 2024-09-25 | 752 days |

## Coding

Writing code, patching repositories, and coding agents

110 models

| Rank | Model | Model ID | Lab | Overall | Intelligence | Coding | Released | Age |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Claude Opus 5.5 | anthropic/claude-opus-5-5 | Anthropic | 100.0 | 98.9 | 100.0 | 2026-09-22 | 25 days |
| 2 | GPT-6 Astra | openai/gpt-6-astra | OpenAI | 96.6 | 94.1 | 98.3 | 2026-09-04 | 43 days |
| 3 | Claude Sonnet 5.5 | anthropic/claude-sonnet-5-5 | Anthropic | 97.4 | 96.0 | 97.9 | 2026-09-28 | 19 days |
| 4 | GPT-6.1 Sol | openai/gpt-6.1-sol | OpenAI | 96.3 | 94.5 | 97.2 | 2026-09-29 | 18 days |
| 5 | Claude Fable 5.1 | anthropic/claude-fable-5-1 | Anthropic | 98.1 | 98.6 | 96.2 | 2026-09-01 | 46 days |
| 6 | Claude Opus 5 | anthropic/claude-opus-5 | Anthropic | 96.7 | 98.4 | 93.3 | 2026-07-24 | 85 days |
| 7 | GPT-6 Sol | openai/gpt-6-sol | OpenAI | 92.6 | 91.2 | 93.1 | 2026-09-22 | 25 days |
| 8 | Gemini 4 Argon | google/gemini-4-argon | Google | 97.3 | 100.0 | 92.6 | 2026-10-13 | 4 days |
| 9 | Qwen3.8 Max 0902 | alibaba/qwen3.8-max-0902 | Alibaba | 95.4 | 96.8 | 92.4 | 2026-09-02 | 45 days |
| 10 | Qwen3.8 Max | alibaba/qwen3.8-max | Alibaba | 95.4 | 96.8 | 92.3 | 2026-08-03 | 75 days |
| 11 | Muse Spark 1.3 | meta/muse-spark-1.3 | Meta | 95.3 | 97.2 | 91.6 | 2026-09-02 | 45 days |
| 12 | Kimi K3 | moonshotai/kimi-k3 | Moonshot AI | 94.6 | 96.2 | 91.4 | 2026-07-16 | 93 days |
| 13 | Muse Wonder | meta/muse-wonder-1.0 | Meta | 95.5 | 98.0 | 91.2 | 2026-10-12 | 5 days |
| 14 | Grok 4.7 | xai/grok-4.7 | xAI | 91.6 | 91.4 | 90.6 | 2026-09-21 | 26 days |
| 15 | MiMo-V2.6-Flash | xiaomi/mimo-v2.6-flash | Xiaomi | 93.5 | 95.0 | 90.3 | 2026-09-22 | 25 days |
| 16 | Qwen3.8 Flash Next | alibaba/qwen3.8-flash-next | Alibaba | 90.7 | — | 90.2 | 2026-08-27 | 51 days |
| 17 | Hy4 preview | tencent/hy4-preview | Tencent | 90.6 | — | 90.1 | 2026-08-28 | 50 days |
| 18 | MiMo-V2.6-Pro | xiaomi/mimo-v2.6-pro | Xiaomi | 94.5 | 97.3 | 89.7 | 2026-09-22 | 25 days |
| 19 | Claude Fable 5 | anthropic/claude-fable-5 | Anthropic | 94.5 | 97.3 | 89.7 | 2026-06-09 | 130 days |
| 20 | GLM-5.3 | zhipuai/glm-5.3 | Zhipu AI | 93.6 | 96.0 | 89.5 | 2026-08-14 | 64 days |
| 21 | DeepSeek V4.1 Flash | deepseek/deepseek-v4.1-flash | DeepSeek | 93.3 | 95.5 | 89.4 | 2026-09-10 | 37 days |
| 22 | GPT-5.6 Sol | openai/gpt-5.6-sol | OpenAI | 93.1 | 95.1 | 89.3 | 2026-07-09 | 100 days |
| 23 | Grok 4.6 | xai/grok-4.6 | xAI | 92.0 | 93.2 | 89.3 | 2026-08-12 | 66 days |
| 24 | GLM-5.3-Flash | zhipuai/glm-5.3-flash | Zhipu AI | 93.3 | 96.0 | 88.7 | 2026-08-26 | 52 days |
| 25 | GLM-5.2 | zhipuai/glm-5.2 | Zhipu AI | 93.2 | 96.0 | 88.6 | 2026-06-13 | 126 days |
| 26 | Qwen3.8 27B | alibaba/qwen3.8-27b | Alibaba | 91.9 | 94.0 | 88.0 | 2026-08-14 | 64 days |
| 27 | Gemini 3.7 Flash | google/gemini-3.7-flash | Google | 93.5 | 97.1 | 87.8 | 2026-08-13 | 65 days |
| 28 | Gemini 3.8 Flash | google/gemini-3.8-flash | Google | 93.7 | 97.8 | 87.5 | 2026-09-02 | 45 days |
| 29 | Claude Haiku 5.5 | anthropic/claude-haiku-5-5 | Anthropic | 88.0 | — | 87.5 | 2026-10-07 | 10 days |
| 30 | DeepSeek V4 Flash | deepseek/deepseek-v4-flash | DeepSeek | 91.2 | 93.4 | 87.3 | 2026-04-24 | 176 days |
| 31 | GPT-6 Luna | openai/gpt-6-luna | OpenAI | 89.8 | 90.8 | 87.3 | 2026-09-22 | 25 days |
| 32 | Step 5 Preview | stepfun/step-5-preview | StepFun | 91.1 | 94.1 | 86.3 | 2026-09-16 | 31 days |
| 33 | Claude Opus 4.7 | anthropic/claude-opus-4-7 | Anthropic | 92.7 | 97.2 | 86.0 | 2026-04-16 | 184 days |
| 34 | Claude Opus 4.8 | anthropic/claude-opus-4-8 | Anthropic | 91.6 | 95.3 | 85.9 | 2026-05-28 | 142 days |
| 35 | Grok 4.5 | xai/grok-4.5 | xAI | 91.1 | 94.5 | 85.7 | 2026-07-08 | 101 days |
| 36 | Claude Opus 4.6 | anthropic/claude-opus-4-6 | Anthropic | 92.9 | 98.0 | 85.4 | 2026-02-05 | 254 days |
| 37 | Muse Spark 1.1 | meta/muse-spark-1.1 | Meta | 92.0 | 96.5 | 85.2 | 2026-04-08 | 192 days |
| 38 | Mistral Large 4 | mistral/mistral-large-4 | Mistral | 90.2 | 93.3 | 85.2 | 2026-10-06 | 11 days |
| 39 | Claude Sonnet 5 | anthropic/claude-sonnet-5 | Anthropic | 90.6 | 94.1 | 85.0 | 2026-06-30 | 109 days |
| 40 | Gemini 3.6 Flash | google/gemini-3.6-flash | Google | 91.8 | 96.5 | 84.9 | 2026-07-21 | 88 days |
| 41 | Muse Spark 1.2 | meta/muse-spark-1.2 | Meta | 91.9 | 96.8 | 84.7 | 2026-08-05 | 73 days |
| 42 | Claude Sonnet 4.6 | anthropic/claude-sonnet-4-6 | Anthropic | 90.7 | 95.1 | 84.1 | 2026-02-17 | 242 days |
| 43 | GPT-5.6 Terra | openai/gpt-5.6-terra | OpenAI | 90.3 | 94.5 | 84.0 | 2026-07-09 | 100 days |
| 44 | GPT-5.6 Luna | openai/gpt-5.6-luna | OpenAI | 89.6 | 93.4 | 83.8 | 2026-07-09 | 100 days |
| 45 | GPT-5.5 | openai/gpt-5.5 | OpenAI | 90.9 | 96.0 | 83.5 | 2026-04-23 | 177 days |
| 46 | GLM-5.1 | zhipuai/glm-5.1 | Zhipu AI | 90.5 | 95.4 | 83.3 | 2026-04-07 | 193 days |
| 47 | Kimi K2.6 | moonshotai/kimi-k2.6 | Moonshot AI | 90.3 | 95.0 | 83.3 | 2026-04-21 | 179 days |
| 48 | Hy3 | tencent/hy3 | Tencent | 89.6 | 93.8 | 83.2 | 2026-07-06 | 103 days |
| 49 | Gemini 3.5 Flash | google/gemini-3.5-flash | Google | 91.0 | 96.7 | 82.8 | 2026-05-19 | 151 days |
| 50 | Qwen3.6 Max Preview | alibaba/qwen3.6-max-preview | Alibaba | 89.3 | 94.4 | 81.8 | 2026-04-20 | 180 days |
| 51 | MiniMax-M3 | minimax/MiniMax-M3 | MiniMax | 88.8 | 93.5 | 81.8 | 2026-06-01 | 138 days |
| 52 | MiMo-V2.5-Pro | xiaomi/mimo-v2.5-pro | Xiaomi | 89.9 | 95.6 | 81.7 | 2026-04-22 | 178 days |
| 53 | Kimi K2.7 Code | moonshotai/kimi-k2.7-code | Moonshot AI | 81.9 | — | 81.4 | 2026-06-12 | 127 days |
| 54 | Claude Opus 4.5 | anthropic/claude-opus-4-5-20251101 | Anthropic | 89.1 | 94.7 | 81.1 | 2025-11-01 | 350 days |
| 55 | GPT-5.4 | openai/gpt-5.4 | OpenAI | 89.6 | 95.9 | 80.8 | 2026-03-05 | 226 days |
| 56 | Qwen3.6 Plus | alibaba/qwen3.6-plus | Alibaba | 88.4 | 93.7 | 80.7 | 2026-04-02 | 198 days |
| 57 | Gemini 3.1 Pro Preview | google/gemini-3.1-pro-preview | Google | 89.6 | 96.6 | 79.9 | 2026-02-19 | 240 days |
| 58 | DeepSeek V4 Pro | deepseek/deepseek-v4-pro | DeepSeek | 88.6 | 94.7 | 79.9 | 2026-04-24 | 176 days |
| 59 | Gemini 3 Pro Preview | google/gemini-3-pro-preview | Google | 89.4 | 96.5 | 79.5 | 2025-11-18 | 333 days |
| 60 | Gemini 3.5 Flash Lite | google/gemini-3.5-flash-lite | Google | 87.8 | 93.6 | 79.5 | 2026-07-21 | 88 days |
| 61 | MiMo-V2.5 | xiaomi/mimo-v2.5 | Xiaomi | 87.5 | 93.2 | 79.4 | 2026-04-22 | 178 days |
| 62 | Kimi K2.5 | moonshotai/kimi-k2.5 | Moonshot AI | 88.1 | 94.3 | 79.3 | 2026-01 | 289 days |
| 63 | GLM-5 | zhipuai/glm-5 | Zhipu AI | 88.1 | 94.4 | 79.2 | 2026-02-12 | 247 days |
| 64 | GLM-4.7 | zhipuai/glm-4.7 | Zhipu AI | 87.7 | 93.7 | 79.2 | 2025-12-22 | 299 days |
| 65 | MiMo-V2-Pro | xiaomi/mimo-v2-pro | Xiaomi | 87.7 | 93.7 | 79.1 | 2026-03-18 | 213 days |
| 66 | GPT-5.2 | openai/gpt-5.2 | OpenAI | 86.5 | 92.4 | 78.2 | 2025-12-11 | 310 days |
| 67 | GPT-5 | openai/gpt-5 | OpenAI | 86.2 | 91.8 | 78.2 | 2025-08-07 | 436 days |
| 68 | Inkling | thinkingmachines/inkling | Thinking Machines | 87.4 | 94.1 | 78.0 | 2026-07-15 | 94 days |
| 69 | Inkling Small | thinkingmachines/inkling-small | Thinking Machines | 86.2 | 92.2 | 77.8 | 2026-07-30 | 79 days |
| 70 | GPT-5.3 Codex | openai/gpt-5.3-codex | OpenAI | 78.1 | — | 77.6 | 2026-02-05 | 254 days |
| 71 | GLM-5V-Turbo | zhipuai/glm-5v-turbo | Zhipu AI | 86.9 | 93.8 | 77.4 | 2026-04-01 | 199 days |
| 72 | Qwen3.5 397B-A17B | alibaba/qwen3.5-397b-a17b | Alibaba | 86.9 | 93.8 | 77.3 | 2026-02-15 | 244 days |
| 73 | GPT-5.4 mini | openai/gpt-5.4-mini | OpenAI | 85.9 | 92.1 | 77.2 | 2026-03-17 | 214 days |
| 74 | MiniMax-M2.7 | minimax/MiniMax-M2.7 | MiniMax | 85.7 | 91.7 | 77.2 | 2026-03-18 | 213 days |
| 75 | GPT-5.1 | openai/gpt-5.1 | OpenAI | 87.0 | 94.2 | 77.0 | 2025-11-13 | 338 days |
| 76 | Claude Opus 4.1 | anthropic/claude-opus-4-1-20250805 | Anthropic | 86.0 | 92.6 | 76.7 | 2025-08-05 | 438 days |
| 77 | Claude Sonnet 4.5 | anthropic/claude-sonnet-4-5-20250929 | Anthropic | 86.6 | 93.9 | 76.5 | 2025-09-29 | 383 days |
| 78 | MiniMax-M2.5 | minimax/MiniMax-M2.5 | MiniMax | 83.7 | 88.7 | 76.5 | 2026-02-12 | 247 days |
| 79 | Solar Pro 4 | upstage/solar-pro4 | Upstage | 84.4 | 90.5 | 75.7 | 2026-08-06 | 72 days |
| 80 | DeepSeek V3.2 | deepseek/deepseek-v3.2 | DeepSeek | 85.5 | 93.0 | 75.2 | 2025-12-01 | 320 days |
| 81 | Qwen3.5 122B-A10B | alibaba/qwen3.5-122b-a10b | Alibaba | 85.2 | 92.5 | 75.1 | 2026-02-23 | 236 days |
| 82 | Qwen3.5 27B | alibaba/qwen3.5-27b | Alibaba | 84.8 | 91.9 | 75.0 | 2026-02-23 | 236 days |
| 83 | Grok 4.3 | xai/grok-4.3 | xAI | 84.4 | 91.2 | 74.9 | 2026-04-17 | 183 days |
| 84 | Laguna M.1 | poolside/laguna-m.1 | Poolside | 75.0 | — | 74.5 | 2026-04-28 | 172 days |
| 85 | GLM-4.6 | zhipuai/glm-4.6 | Zhipu AI | 85.5 | 94.0 | 74.0 | 2025-09-30 | 382 days |
| 86 | GPT-5.2 Codex | openai/gpt-5.2-codex | OpenAI | 74.3 | — | 73.9 | 2025-12-11 | 310 days |
| 87 | GPT-5.1 Codex | openai/gpt-5.1-codex | OpenAI | 74.2 | — | 73.8 | 2025-11-13 | 338 days |
| 88 | GPT-5.1 Codex Max | openai/gpt-5.1-codex-max | OpenAI | 74.2 | — | 73.8 | 2025-11-13 | 338 days |
| 89 | MiMo-V2-Flash | xiaomi/mimo-v2-flash | Xiaomi | 84.2 | 92.1 | 73.4 | 2025-12-16 | 305 days |
| 90 | Claude Haiku 4.5 | anthropic/claude-haiku-4-5-20251001 | Anthropic | 83.6 | 91.1 | 73.4 | 2025-10-15 | 367 days |
| 91 | Kimi K2 Thinking Turbo | moonshotai/kimi-k2-thinking-turbo | Moonshot AI | 84.1 | 92.3 | 73.0 | 2025-11-06 | 345 days |
| 92 | Laguna XS.2 | poolside/laguna-xs.2 | Poolside | 72.3 | — | 71.9 | 2026-04-28 | 172 days |
| 93 | MiniMax-M2 | minimax/MiniMax-M2 | MiniMax | 80.8 | 87.4 | 71.6 | 2025-10-27 | 355 days |
| 94 | Qwen3-Coder 480B-A35B Instruct | alibaba/qwen3-coder-480b-a35b-instruct | Alibaba | 80.8 | 88.5 | 70.4 | 2025-04 | 564 days |
| 95 | Mistral Medium 3.5 | mistral/mistral-medium-3-5 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-30 | 170 days |
| 96 | Mistral Medium 3.5 | mistral/mistral-medium-2604 | Mistral | 82.9 | 92.7 | 69.8 | 2026-04-29 | 171 days |
| 97 | Gemini 3.1 Flash Lite Preview | google/gemini-3.1-flash-lite-preview | Google | 82.5 | 92.4 | 69.4 | 2026-03-03 | 228 days |
| 98 | Qwen3.5 35B-A3B | alibaba/qwen3.5-35b-a3b | Alibaba | 81.7 | 91.0 | 69.2 | 2026-02-23 | 236 days |
| 99 | Qwen3.5 Flash | alibaba/qwen3.5-flash | Alibaba | 81.6 | 91.2 | 68.7 | 2026-02-23 | 236 days |
| 100 | GPT-5.1 Codex mini | openai/gpt-5.1-codex-mini | OpenAI | 69.1 | — | 68.7 | 2025-11-13 | 338 days |
| 101 | Grok 4.1 Fast | xai/grok-4.1-fast | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 102 | Grok 4.1 Fast (Reasoning) | xai/grok-4.1-fast-reasoning | xAI | 81.9 | 91.9 | 68.6 | 2025-11-19 | 332 days |
| 103 | Trinity Large Thinking | arcee-ai/trinity-large-thinking | Arcee AI | 79.3 | 87.5 | 68.3 | 2026-04-01 | 199 days |
| 104 | Mistral Large 3 | mistral/mistral-large-2512 | Mistral | 82.3 | 93.2 | 67.9 | 2025-12-02 | 319 days |
| 105 | Gemini 2.5 Pro | google/gemini-2.5-pro | Google | 83.3 | 95.1 | 67.7 | 2025-06-17 | 487 days |
| 106 | Devstral 2 | mistral/devstral-2512 | Mistral | 66.4 | — | 66.0 | 2025-12-09 | 312 days |
| 107 | Mercury 2 | inception/mercury-2 | Inception | 78.2 | 88.4 | 64.6 | 2026-03-04 | 227 days |
| 108 | x-AI/Grok-Code-Fast 1 | xai/grok-code-fast-1 | xAI | 64.8 | — | 64.4 | 2025-09-02 | 410 days |
| 109 | X-Ai/Grok-4-Fast-Reasoning | xai/grok-4-fast-reasoning | xAI | 79.5 | 91.3 | 64.0 | 2025-12-18 | 303 days |
| 110 | Devstral Medium | mistral/devstral-medium-2507 | Mistral | 59.5 | — | 59.1 | 2025-07-10 | 464 days |
