| 1 | ▲ 1 | OGPT-5.2 (xhigh)闭源OpenAI | 50.6 | — | — | — |
| 2 | ▲ 2 | AClaude Opus 4.5 (Reasoning)闭源Anthropic | 49.1 | — | — | — |
| 3 | ▼ 2 | GGemini 3 Pro Preview (high)闭源Google | 47.9 | — | — | — |
| 4 | ▲ 1 | OGPT-5.1 (high)闭源OpenAI | 47.0 | — | — | — |
| 5 | ▼ 2 | GGemini 3 Flash Preview (Reasoning)闭源Google | 45.8 | — | — | — |
| 6 | ▲ 2 | OGPT-5.2 (medium)闭源OpenAI | 45.4 | — | — | — |
| 7 | — | OGPT-5 (high)闭源OpenAI | 44.1 | — | — | — |
| 8 | ▼ 2 | OGPT-5 Codex (high)闭源OpenAI | 44.0 | — | — | — |
| 9 | ▲ 15 | AClaude Opus 4.5 (Non-reasoning)闭源Anthropic | 42.5 | — | — | — |
| 10 | ▲ 7 | AClaude 4.5 Sonnet (Reasoning)闭源Anthropic | 42.4 | — | — | — |
| 11 | ▼ 1 | OGPT-5 (medium)闭源OpenAI | 41.9 | — | — | — |
| 12 | ▼ 3 | OGPT-5.1 Codex (high)闭源OpenAI | 41.6 | — | — | — |
| 13 | ▼ 1 | XGrok 4闭源xAI | 41.4 | — | — | — |
| 14 | ▲ 1 | OGPT-5 mini (high)闭源OpenAI | 40.6 | — | — | — |
| 15 | ▼ 1 | GGemini 3 Pro Preview (low)闭源Google | 40.6 | — | — | — |
| 16 | ▲ 4 | OGPT-5 (low)闭源OpenAI | 38.7 | — | — | — |
| 17 | ▲ 4 | OGPT-5 mini (medium)闭源OpenAI | 38.6 | — | — | — |
| 18 | ▲ 14 | AClaude 4 Sonnet (Reasoning)闭源Anthropic | 38.3 | — | — | — |
| 19 | ▼ 3 | XGrok 4.1 Fast (Reasoning)闭源xAI | 38.2 | — | — | — |
| 20 | ▼ 1 | OGPT-5.1 Codex mini (high)闭源OpenAI | 38.0 | — | — | — |
| 21 | ▲ 13 | AClaude 4.5 Haiku (Reasoning)闭源Anthropic | 36.6 | — | — | — |
| 22 | ▲ 25 | AClaude 4.5 Sonnet (Non-reasoning)闭源Anthropic | 36.6 | — | — | — |
| 23 | ▼ 5 | ANova 2.0 Pro Preview (medium)闭源Amazon | 35.3 | — | — | — |
| 24 | ▲ 11 | GGemini 3 Flash Preview (Non-reasoning)闭源Google | 34.8 | — | — | — |
| 25 | ▼ 2 | XGrok 4 Fast (Reasoning)闭源xAI | 34.6 | — | — | — |
| 26 | ▲ 20 | AClaude 3.7 Sonnet (Reasoning)闭源Anthropic | 34.4 | — | — | — |
| 27 | ▼ 2 | GGemini 2.5 Pro闭源Google | 34.1 | — | — | — |
| 28 | ▲ 25 | OGPT-5.2 (Non-reasoning)闭源OpenAI | 33.1 | — | — | — |
| 29 | ▼ 3 | Oo4-mini (high)闭源OpenAI | 32.9 | — | — | — |
| 30 | ▼ 8 | Ogpt-oss-120B (high)开源OpenAI | 32.9 | — | — | — |
| 31 | ▲ 34 | AClaude 4 Sonnet (Non-reasoning)闭源Anthropic | 32.7 | — | — | — |
| 32 | ▼ 2 | XGrok 3 mini Reasoning (high)闭源xAI | 32.4 | — | — | — |
| 33 | ▼ 4 | ANova 2.0 Pro Preview (low)闭源Amazon | 32.2 | — | — | — |
| 34 | ▲ 2 | GGemini 2.5 Flash Preview (Sep '25) (Reasoning)闭源Google | 30.8 | — | — | — |
| 35 | ▲ 43 | AClaude 3.7 Sonnet (Non-reasoning)闭源Anthropic | 30.6 | — | — | — |
| 36 | ▲ 38 | AClaude 4.5 Haiku (Non-reasoning)闭源Anthropic | 30.5 | — | — | — |
| 37 | ▼ 9 | ANova 2.0 Lite (medium)闭源Amazon | 29.9 | — | — | — |
| 38 | ▼ 5 | ANova 2.0 Omni (medium)闭源Amazon | 27.9 | — | — | — |
| 39 | ▼ 8 | SApriel-v1.6-15B-Thinker开源ServiceNow | 27.8 | — | — | — |
| 40 | ▲ 3 | GGemini 2.5 Flash (Reasoning)闭源Google | 27.2 | — | — | — |
| 41 | ▲ 28 | OGPT-5.1 (Non-reasoning)闭源OpenAI | 27.2 | — | — | — |
| 42 | ▲ 2 | OGPT-5 nano (high)闭源OpenAI | 26.7 | — | — | — |
| 43 | ▲ 5 | OGPT-5 nano (medium)闭源OpenAI | 25.8 | — | — | — |
| 44 | ▲ 24 | OGPT-4.1闭源OpenAI | 25.8 | — | — | — |
| 45 | ▲ 13 | GGemini 2.5 Flash Preview (Sep '25) (Non-reasoning)闭源Google | 25.6 | — | — | — |
| 46 | ▲ 15 | XGrok 3闭源xAI | 25.2 | — | — | — |
| 47 | ▲ 10 | ANova 2.0 Lite (low)闭源Amazon | 25.0 | — | — | — |
| 48 | ▼ 7 | NNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)开源NVIDIA | 24.7 | — | — | — |
| 49 | ▼ 9 | Ogpt-oss-20B (high)开源OpenAI | 24.7 | — | — | — |
| 50 | ▲ 17 | OGPT-5 (minimal)闭源OpenAI | 24.5 | — | — | — |
| 51 | ▼ 2 | ANova 2.0 Omni (low)闭源Amazon | 24.1 | — | — | — |
| 52 | ▲ 3 | Ogpt-oss-120B (low)开源OpenAI | 23.8 | — | — | — |
| 53 | ▲ 33 | XGrok 4.1 Fast (Non-reasoning)闭源xAI | 23.6 | — | — | — |
| 54 | ▲ 18 | ANova 2.0 Pro Preview (Non-reasoning)闭源Amazon | 23.5 | — | — | — |
| 55 | ▲ 15 | OGPT-4.1 mini闭源OpenAI | 22.9 | — | — | — |
| 56 | ▲ 27 | XGrok 4 Fast (Non-reasoning)闭源xAI | 22.8 | — | — | — |
| 57 | ▼ 3 | GGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)闭源Google | 22.3 | — | — | — |
| 58 | ▲ 18 | OGPT-5 mini (minimal)闭源OpenAI | 21.5 | — | — | — |
| 59 | ▲ 7 | Ogpt-oss-20B (low)开源OpenAI | 21.2 | — | — | — |
| 60 | ▲ 20 | GGemini 2.5 Flash (Non-reasoning)闭源Google | 20.9 | — | — | — |
| 61 | ▲ 14 | GGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)闭源Google | 20.1 | — | — | — |
| 62 | — | NLlama Nemotron Super 49B v1.5 (Reasoning)开源NVIDIA | 19.4 | — | — | — |
| 63 | ▲ 36 | ANova Premier闭源Amazon | 19.2 | — | — | — |
| 64 | ▲ 34 | GGemini 2.0 Flash (Feb '25)闭源Google | 18.9 | — | — | — |
| 65 | ▲ 25 | MLlama 4 Maverick开源Meta | 18.9 | — | — | — |
| 66 | ▲ 25 | ANova 2.0 Lite (Non-reasoning)闭源Amazon | 18.8 | — | — | — |
| 67 | ▲ 14 | GGemini 2.5 Flash-Lite (Reasoning)闭源Google | 17.9 | — | — | — |
| 68 | ▲ 41 | MLlama 3.1 Instruct 405B开源Meta | 17.5 | — | — | — |
| 69 | ▲ 28 | ANova 2.0 Omni (Non-reasoning)闭源Amazon | 17.2 | — | — | — |
| 70 | ▲ 18 | NNVIDIA Nemotron Nano 9B V2 (Reasoning)开源NVIDIA | 15.5 | — | — | — |
| 71 | ▲ 43 | NLlama Nemotron Super 49B v1.5 (Non-reasoning)开源NVIDIA | 15.4 | — | — | — |
| 72 | ▲ 7 | NNVIDIA Nemotron Nano 12B v2 VL (Reasoning)开源NVIDIA | 15.1 | — | — | — |
| 73 | ▲ 37 | MLlama 3.3 Instruct 70B开源Meta | 15.1 | — | — | — |
| 74 | ▲ 34 | MLlama 4 Scout开源Meta | 14.0 | — | — | — |
| 75 | ▲ 52 | NLlama 3.1 Nemotron Instruct 70B开源NVIDIA | 14.0 | — | — | — |
| 76 | ▲ 28 | OGPT-5 nano (minimal)闭源OpenAI | 14.0 | — | — | — |
| 77 | ▲ 42 | NNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)开源NVIDIA | 13.9 | — | — | — |
| 78 | ▲ 11 | NNVIDIA Nemotron Nano 9B V2 (Non-reasoning)开源NVIDIA | 13.8 | — | — | — |
| 79 | ▲ 32 | OGPT-4.1 nano闭源OpenAI | 13.4 | — | — | — |
| 80 | ▲ 21 | GGemini 2.5 Flash-Lite (Non-reasoning)闭源Google | 13.0 | — | — | — |
| 81 | ▲ 53 | ANova Lite闭源Amazon | 12.5 | — | — | — |
| 82 | ▲ 64 | MLlama 3.1 Instruct 8B开源Meta | 12.2 | — | — | — |
| 83 | ▲ 46 | IGranite 4.0 H Small开源IBM | 11.5 | — | — | — |
| 84 | ▲ 48 | GGemma 3 27B Instruct开源Google | 10.5 | — | — | — |
| 85 | ▲ 36 | NNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)开源NVIDIA | 10.4 | — | — | — |
| 86 | ▲ 51 | GGemma 3 12B Instruct开源Google | 9.4 | — | — | — |
| 87 | ▲ 68 | IGranite 4.0 H 1B开源IBM | 8.4 | — | — | — |
| 88 | ▲ 75 | LLFM2 2.6B开源Liquid AI | 7.9 | — | — | — |
| 89 | ▲ 68 | IGranite 4.0 1B开源IBM | 7.7 | — | — | — |
| 90 | ▲ 55 | LLFM2 8B A1B开源Liquid AI | 7.3 | — | — | — |
| 91 | ▲ 83 | IGranite 4.0 350M开源IBM | 7.2 | — | — | — |
| 92 | ▲ 75 | LLFM2 1.2B开源Liquid AI | 6.8 | — | — | — |
| 93 | ▲ 60 | GGemma 3 4B Instruct开源Google | 6.6 | — | — | — |
| 94 | ▲ 57 | GGemma 3n E4B Instruct开源Google | 6.3 | — | — | — |
| 95 | ▲ 78 | IGranite 4.0 H 350M开源IBM | 6.0 | — | — | — |