AA Intelligence Index leaderboard
99 models ranked, highest score first.
| # | Model | Company | Score |
|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | 61.4 |
| 2 | GPT-5.5 | OpenAI | 60.2 |
| 3 | Claude Opus 4.7 | Anthropic | 57.3 |
| 4 | Gemini 3.1 Pro Preview | 57.2 | |
| 5 | GPT-5.4 | OpenAI | 56.8 |
| 6 | Qwen3.7 Max | Alibaba | 56.6 |
| 7 | MiniMax-M3 | MiniMax | 54.7 |
| 8 | Kimi K2.6 | Kimi | 53.9 |
| 9 | MiMo-V2.5-Pro | Xiaomi | 53.8 |
| 10 | GPT-5.3 Codex | OpenAI | 53.6 |
| 11 | Qwen3.7 Plus | Alibaba | 53.3 |
| 12 | Grok 4.3 | xAI | 53.2 |
| 13 | Muse Spark | Meta | 52.2 |
| 14 | Qwen3.6 Max Preview | Alibaba | 51.8 |
| 15 | DeepSeek V4 Pro | DeepSeek | 51.5 |
| 16 | GLM-5.1 | Z AI | 51.4 |
| 17 | GPT-5.2 | OpenAI | 51.3 |
| 18 | Qwen3.6 Plus | Alibaba | 50.0 |
| 19 | Claude Opus 4.5 | Anthropic | 49.7 |
| 20 | MiniMax-M2.7 | MiniMax | 49.6 |
| 21 | Grok 4.20 0309 v2 | xAI | 49.3 |
| 22 | MiMo-V2-Pro | Xiaomi | 49.2 |
| 23 | MiMo-V2.5 | Xiaomi | 49.0 |
| 24 | GPT-5.4 mini | OpenAI | 48.9 |
| 25 | Grok 4.20 0309 | xAI | 48.5 |
| 26 | Nemotron 3 Ultra 550B A55B | NVIDIA | 47.7 |
| 27 | GPT-5.1 | OpenAI | 47.7 |
| 28 | GLM-5-Turbo | Z AI | 46.8 |
| 29 | DeepSeek V4 Flash | DeepSeek | 46.5 |
| 30 | Qwen3.6 27B | Alibaba | 45.8 |
| 31 | Qwen3.5 397B A17B | Alibaba | 45.0 |
| 32 | MiMo-V2-Omni-0327 | Xiaomi | 44.9 |
| 33 | GPT-5.4 nano | OpenAI | 44.0 |
| 34 | Qwen3.6 35B A3B | Alibaba | 43.5 |
| 35 | MiMo-V2-Omni | Xiaomi | 43.4 |
| 36 | Gemini 3.5 Flash | 43.3 | |
| 37 | GLM 5V Turbo | Z AI | 42.9 |
| 38 | Step 3.7 Flash | StepFun | 42.6 |
| 39 | Claude Sonnet 4.6 | Anthropic | 42.6 |
| 40 | Qwen3.5 27B | Alibaba | 42.1 |
| 41 | Hy3-preview | Tencent | 41.9 |
| 42 | GPT-5.5 Instant | OpenAI | 41.8 |
| 43 | DeepSeek V3.2 | DeepSeek | 41.7 |
| 44 | Qwen3.5 122B A10B | Alibaba | 41.6 |
| 45 | Mistral Medium 3.5 | Mistral | 39.2 |
| 46 | Gemma 4 31B | 39.2 | |
| 47 | Qwen3.5 Omni Plus | Alibaba | 38.6 |
| 48 | Ring-2.6-1T | InclusionAI | 38.5 |
| 49 | Step 3.5 Flash 2603 | StepFun | 38.5 |
| 50 | Qwen3.5 35B A3B | Alibaba | 37.1 |
| 51 | JT-35B-Flash | China Mobile | 36.1 |
| 52 | NVIDIA Nemotron 3 Super 120B A12B | NVIDIA | 36.0 |
| 53 | Ling-2.6-1T | InclusionAI | 33.6 |
| 54 | Gemini 3.1 Flash-Lite Preview | 33.5 | |
| 55 | Mercury 2 | Inception | 32.8 |
| 56 | Qwen3.5 9B | Alibaba | 32.4 |
| 57 | Trinity Large Thinking | Arcee AI | 31.9 |
| 58 | Gemma 4 26B A4B | 31.2 | |
| 59 | EXAONE 4.5 33B | LG AI Research | 30.2 |
| 60 | Gemma 4 12B | 29.0 | |
| 61 | Nemotron Cascade 2 30B A3B | NVIDIA | 28.4 |
| 62 | Mistral Small 4 | Mistral | 27.8 |
| 63 | Qwen3.5 4B | Alibaba | 27.1 |
| 64 | Gemini 2.5 Flash | 27.0 | |
| 65 | Ling 2.6 Flash | InclusionAI | 26.2 |
| 66 | Solar Pro 3 | Upstage | 25.9 |
| 67 | Qwen3.5 Omni Flash | Alibaba | 25.9 |
| 68 | JT-MINI | China Mobile | 25.4 |
| 69 | GPT-5 | OpenAI | 23.9 |
| 70 | Mistral Large 3 | Mistral | 22.8 |
| 71 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 21.4 |
| 72 | Gemma 4 E4B | 18.8 | |
| 73 | MiniCPM5-1B | OpenBMB | 18.2 |
| 74 | Sarvam 105B | Sarvam | 18.2 |
| 75 | Claude 3 Opus | Anthropic | 18.0 |
| 76 | Gemini 2.0 Flash | 16.8 | |
| 77 | DeepSeek-V3 | DeepSeek | 16.5 |
| 78 | Qwen3.5 2B | Alibaba | 16.3 |
| 79 | Gemma 4 E2B | 15.2 | |
| 80 | Granite 4.1 30B | IBM | 14.7 |
| 81 | NVIDIA Nemotron 3 Nano 4B | NVIDIA | 14.7 |
| 82 | Claude 3.5 Sonnet | Anthropic | 14.2 |
| 83 | Grok-2 | xAI | 13.9 |
| 84 | GPT-4 Turbo | OpenAI | 13.7 |
| 85 | GPT-4 | OpenAI | 12.8 |
| 86 | MiniCPM-V 4.6 1.3B | OpenBMB | 12.7 |
| 87 | Granite 4.1 8B | IBM | 12.4 |
| 88 | Sarvam 30B | Sarvam | 12.3 |
| 89 | Claude 3 Haiku | Anthropic | 12.3 |
| 90 | Gemini 1.5 Pro | 12.0 | |
| 91 | Grok-1 | xAI | 11.7 |
| 92 | Qwen3.5 0.8B | Alibaba | 10.5 |
| 93 | LFM2 24B A2B | Liquid AI | 10.5 |
| 94 | Claude 3 Sonnet | Anthropic | 10.3 |
| 95 | Mistral Large | Mistral | 9.9 |
| 96 | Claude 2.1 | Anthropic | 9.3 |
| 97 | PaLM 2 | 8.6 | |
| 98 | Granite 4.1 3B | IBM | 8.5 |
| 99 | Tiny Aya Global | Cohere | 4.7 |