| 1 | Gemini 4 Argon (High)Google | 100 | — | 1,536 | — |
| 2 | Claude Fable 5.1 (Max)Anthropic | 98.4 | — | 1,526 | — |
| 3 | Claude Opus 5 (High)Anthropic | 97.7 | — | 1,521 | — |
| 4 | Claude Fable 5 (High)Anthropic | 97.5 | — | 1,520 | — |
| 5 | Gemini 3.8 Flash (High)Google | 97.3 | — | 1,519 | — |
| 6 | Claude Opus 4.6 (High)Anthropic | 96.8 | — | 1,516 | — |
| 7 | Claude Opus 5.5 (High)Anthropic | 96.6 | — | 1,514 | — |
| 8 | GPT 6.1 SolOpenAI | 95.3 | 92.6 | — | 76.3 |
| 9 | Muse Spark 1.3 (Max)Meta | 95.3 | — | 1,506 | — |
| 10 | Claude Opus 4.7 (High)Anthropic | 94.9 | — | 1,503 | — |
| 11 | Kimi K3 (Max)Moonshot | 94.7 | — | 1,502 | — |
| 12 | Gemini 3.7 Flash (High)Google | 94.6 | — | 1,502 | — |
| 13 | GLM 5.3 (Max)Zhipu | 94.6 | — | 1,501 | — |
| 14 | Gemini 3.6 Flash (High)Google | 94.5 | — | 1,501 | — |
| 15 | GPT 5.5OpenAI | 94.4 | — | 1,500 | — |
| 16 | Gemini 3.5 Flash (High)Google | 94.0 | — | 1,497 | — |
| 17 | Gemini 4 Hydrogen (High)Google | 93.6 | — | 1,495 | — |
| 18 | DeepSeek v4.1 Flash 20260910 (Max)DeepSeek | 93.6 | — | 1,495 | — |
| 19 | GPT 5.6 Sol (xHigh)OpenAI | 93.5 | — | 1,494 | — |
| 20 | Muse Spark 1.1Meta | 93.3 | — | 1,493 | — |
| 21 | Claude Opus 4.8 (High)Anthropic | 93.2 | — | 1,492 | — |
| 22 | GPT 5.4 (High)OpenAI | 92.9 | — | 1,491 | — |
| 23 | Muse Wonder (Max)Meta | 92.8 | — | 1,490 | — |
| 24 | Gemini 3.1 Pro PreviewGoogle | 92.5 | — | 1,488 | — |
| 25 | GLM 5.2 (Max)zai | 92.3 | — | 1,487 | — |
| 26 | Muse Spark 1.2 (xHigh)Meta | 92.2 | — | 1,486 | — |
| 27 | Claude Sonnet 5.5 (xHigh)Anthropic | 92.2 | — | 1,486 | — |
| 28 | Hy3Tencent | 91.9 | — | 1,484 | — |
| 29 | qwen3.7 Max PreviewAlibaba | 91.8 | — | 1,483 | — |
| 30 | GPT 6 Astra (Max)OpenAI | 91.4 | — | 1,481 | — |
| 31 | Kimi k2.6Moonshot | 91.1 | — | 1,479 | — |
| 32 | Mimo v2.5 Proxiaomi | 91.1 | — | 1,479 | — |
| 33 | GPT 5.6 Terra (xHigh)OpenAI | 91.0 | — | 1,478 | — |
| 34 | Ernie 5.1Baidu | 90.9 | — | 1,478 | — |
| 35 | GPT 5.6 Luna (xHigh)OpenAI | 90.7 | — | 1,476 | — |
| 36 | Gemini 3 ProGoogle | 90.4 | — | 1,475 | — |
| 37 | Gemini 3 FlashGoogle | 90.4 | — | 1,474 | — |
| 38 | GLM 5.1zai | 90.4 | — | 1,474 | — |
| 39 | Claude Opus 4.5 High 32k 20251101Anthropic | 90.1 | — | 1,472 | — |
| 40 | Claude Sonnet 5 (High)Anthropic | 90.1 | — | 1,472 | — |
| 41 | Darwin 180b Rsi R3VIDRAFT | 90.0 | — | — | 73.7 |
| 42 | qwen3.6 Max PreviewAlibaba | 89.9 | — | 1,471 | — |
| 43 | Beam 1.0 501b A23breflection | 89.9 | — | 1,471 | — |
| 44 | Grok 4.5xAI | 89.8 | — | 1,470 | — |
| 45 | Kimi k2.5 (Thinking)Moonshot | 89.6 | — | 1,470 | — |
| 46 | Gemma 4 26b A4bGoogle | 89.6 | — | 1,469 | — |
| 47 | Muse SparkMeta | 89.5 | — | 1,469 | — |
| 48 | qwen3.5 Max PreviewAlibaba | 89.3 | — | 1,468 | — |
| 49 | qwen3.7 PlusAlibaba | 89.0 | — | 1,465 | — |
| 50 | DeepSeek V4 Pro Preview (High)DeepSeek | 88.9 | — | 1,465 | — |
| 51 | Grok 4.20 Beta Reasoning 0309xAI | 88.8 | — | 1,464 | — |
| 52 | GPT 5.5 InstantOpenAI | 88.5 | — | 1,462 | — |
| 53 | Claude Opus 4.5 20251101Anthropic | 88.5 | — | 1,462 | — |
| 54 | Claude Sonnet 4.6Anthropic | 88.4 | — | 1,461 | — |
| 55 | GPT 5.1 (High)OpenAI | 87.9 | — | 1,458 | — |
| 56 | GPT 5.2 (High)OpenAI | 87.6 | — | 1,457 | — |
| 57 | Claude Sonnet 4.5 High 32k 20250929Anthropic | 87.4 | — | 1,455 | — |
| 58 | Grok 4.20 Multi Agent Beta 0309xAI | 87.4 | — | 1,455 | — |
| 59 | Gemini 3 Flash MinimalGoogle | 87.1 | — | 1,453 | — |
| 60 | GPT 5.2 Chat 20260210OpenAI | 87.0 | — | 1,453 | — |
| 61 | Inkling SmallThinking Machines | 86.9 | — | 1,452 | — |
| 62 | qwen3.6 PlusAlibaba | 86.8 | — | 1,451 | — |
| 63 | Claude Haiku 5.5 (High)Anthropic | 86.7 | — | 1,451 | — |
| 64 | Mimo V2 Proxiaomi | 86.6 | — | 1,450 | — |
| 65 | qwen3.5 397b A17bAlibaba | 86.6 | — | 1,450 | — |
| 66 | DeepSeek V4 Pro High 20260813DeepSeek | 86.5 | — | 1,449 | — |
| 67 | GPT 6 Luna (Max)OpenAI | 86.5 | — | 1,449 | — |
| 68 | Dola Seed 2.0 ProByteDance | 86.4 | — | 1,449 | — |
| 69 | Grok 4.20 Beta 1xAI | 86.4 | — | 1,449 | — |
| 70 | O3 2025 04 16OpenAI | 86.3 | — | 1,448 | — |
| 71 | Grok 4.7 (xHigh)xAI | 86.2 | — | 1,447 | — |
| 72 | Grok 4.6 (High)xAI | 85.8 | — | 1,445 | — |
| 73 | Claude Opus 4.1 (Thinking)Anthropic | 85.6 | — | 1,443 | — |
| 74 | DeepSeek V4 ProDeepSeek | 85.5 | — | 1,443 | — |
| 75 | GLM 5Z-AI | 85.5 | — | 1,443 | — |
| 76 | Grok 4.1 (Thinking)xAI | 85.5 | — | 1,443 | — |
| 77 | Nvidia Nemotron 3 Ultra 550b A55b Nvfp4NVIDIA | 85.4 | — | 1,442 | — |
| 78 | Muse GlimmerMeta | 85.4 | — | 1,442 | — |
| 79 | Gemini 3.5 Flash LiteGoogle | 85.4 | — | 1,442 | — |
| 80 | Kimi k2.5 InstantMoonshot | 85.2 | — | 1,441 | — |
| 81 | DeepSeek V4 Flash Preview (High)DeepSeek | 85.2 | — | 1,441 | — |
| 82 | GPT 6 Sol (Max)OpenAI | 85.1 | — | 1,440 | — |
| 83 | Gemini 2.5 ProGoogle | 84.9 | — | 1,439 | — |
| 84 | GPT 5.4 Mini (High)OpenAI | 84.9 | — | 1,439 | — |
| 85 | qwen3.8 (Max)Alibaba | 84.7 | 88.2 | 1,505 | — |
| 86 | Mimo v2.5xiaomi | 84.6 | — | 1,437 | — |
| 87 | Gemini 3.1 Flash Lite PreviewGoogle | 84.4 | — | 1,436 | — |
| 88 | Kimi K2 Thinking TurboMoonshot | 84.4 | — | 1,435 | — |
| 89 | GPT 5 (High)OpenAI | 84.3 | — | 1,435 | — |
| 90 | Ernie 5.0 0110Baidu | 84.1 | — | 1,434 | — |
| 91 | Longcat Flash Chat Exp 2602meituan | 84.0 | — | 1,433 | — |
| 92 | Claude Opus 4.1 20250805Anthropic | 84.0 | — | 1,433 | — |
| 93 | Qwen3 Max PreviewAlibaba | 84.0 | — | 1,433 | — |
| 94 | Mimo V2 Omnixiaomi | 83.9 | — | 1,433 | — |
| 95 | GPT 5.3 ChatOpenAI | 83.6 | — | 1,431 | — |
| 96 | Hy3 PreviewTencent | 83.4 | — | 1,429 | — |
| 97 | DeepSeek v3.2 (Thinking)DeepSeek | 83.3 | — | 1,428 | — |
| 98 | Gemini 4 CarbonGoogle | 83.2 | 90.6 | — | — |
| 99 | Muse Wonder 1.0Meta | 83.2 | 90.6 | — | — |
| 100 | Claude Sonnet 4.5 20250929Anthropic | 83.0 | — | 1,427 | — |
| 101 | GLM 4.7zai | 83.0 | — | 1,427 | — |
| 102 | Mistral Medium 3.5Mistral | 82.9 | — | 1,426 | — |
| 103 | Qwen3 Max 2025 09 23Alibaba | 82.8 | — | 1,426 | — |
| 104 | Grok 4 0709xAI | 82.7 | — | 1,425 | — |
| 105 | qwen3.5 122b A10bAlibaba | 82.7 | — | 1,425 | — |
| 106 | Amazon Nova Experimental Chat 26 02 10Amazon | 82.7 | — | 1,425 | — |
| 107 | DeepSeek V4 FlashDeepSeek | 82.7 | — | 1,424 | — |
| 108 | GPT 5.4 Nano (High)OpenAI | 82.6 | — | 1,424 | — |
| 109 | Grok 4 Fast Non ReasoningxAI | 82.5 | — | 1,424 | — |
| 110 | qwen3.5 27bAlibaba | 82.4 | — | 1,423 | — |
| 111 | MiniMax m2.7MiniMax | 82.4 | — | 1,423 | — |
| 112 | DeepSeek v3.2 Exp (Thinking)DeepSeek | 82.1 | — | 1,421 | — |
| 113 | Claude Opus 4 (Thinking)Anthropic | 82.1 | — | 1,421 | — |
| 114 | Grok 4.1 Fast ReasoningxAI | 82.0 | — | 1,420 | — |
| 115 | Grok 4.3xAI | 81.8 | — | 1,419 | — |
| 116 | GLM 4.6Z.ai | 81.6 | — | 1,418 | — |
| 117 | O4 Mini 2025 04 16OpenAI | 81.6 | — | 1,418 | — |
| 118 | Nvidia Nemotron 3.5 Super Vl 120b A12b Nvfp4NVIDIA | 81.4 | — | 1,417 | — |
| 119 | Qwen3 235b A22b Instruct 2507Alibaba | 81.4 | — | 1,416 | — |
| 120 | Kimi K2 Preview 0905Moonshot | 81.3 | — | 1,416 | — |
| 121 | Solar Pro 4Upstage | 81.1 | — | 1,414 | — |
| 122 | DeepSeek v3.1 (Thinking)DeepSeek | 81.1 | — | 1,414 | — |
| 123 | Qwen3 Next 80b A3b InstructAlibaba | 81.0 | — | 1,414 | — |
| 124 | Longcat Flash Chatmeituan | 80.9 | — | 1,413 | — |
| 125 | DeepSeek R1DeepSeek | 80.7 | — | 1,412 | — |
| 126 | GLM 4.5Z.ai | 80.6 | — | 1,411 | — |
| 127 | Ernie 5.0 Preview 1203Baidu | 80.6 | — | 1,411 | — |
| 128 | Grok 4 Fast ReasoningxAI | 80.5 | — | 1,411 | — |
| 129 | GPT 5 ChatOpenAI | 80.5 | — | 1,410 | — |
| 130 | Qwen3 Vl 235b A22b InstructAlibaba | 80.3 | — | 1,409 | — |
| 131 | Gemini 2.5 Flash Preview 09 2025Google | 80.3 | — | 1,409 | — |
| 132 | O1 2024 12 17OpenAI | 80.2 | — | 1,409 | — |
| 133 | Amazon Nova Experimental Chat 26 01 10Amazon | 80.1 | — | 1,408 | — |
| 134 | GPT 4.5 Preview 2025 02 27OpenAI | 80.0 | — | 1,407 | — |
| 135 | GPT 5 Mini (High)OpenAI | 80.0 | — | 1,407 | — |
| 136 | Step 3.5 FlashStepFun | 79.7 | — | 1,405 | — |
| 137 | O3 Mini (High)OpenAI | 79.6 | — | 1,405 | — |
| 138 | Gemini 2.5 FlashGoogle | 79.6 | — | 1,405 | — |
| 139 | Hunyuan T1 20250711Tencent | 79.6 | — | 1,405 | — |
| 140 | Claude Sonnet 4 (Thinking)Anthropic | 79.5 | — | 1,404 | — |
| 141 | Claude Opus 4 20250514Anthropic | 79.4 | — | 1,403 | — |
| 142 | ChatGPT 4o Latest 20250326OpenAI | 79.3 | — | 1,403 | — |
| 143 | Claude Haiku 4.5 20251001Anthropic | 79.1 | — | 1,402 | — |
| 144 | Mistral Large 3Mistral | 79.1 | — | 1,402 | — |
| 145 | qwen3.5 FlashAlibaba | 79.0 | — | 1,401 | — |
| 146 | DeepSeek v4.1 Flash 1017DeepSeek | 78.8 | 89.1 | — | 71.1 |
| 147 | Qwen3 Vl 235b A22b ThinkingAlibaba | 78.6 | — | 1,398 | — |
| 148 | Qwen3 32bAlibaba | 78.6 | — | 1,398 | — |
| 149 | Amazon Nova Experimental Chat 12 10Amazon | 78.5 | — | 1,398 | — |
| 150 | Qwen3 235b A22b Thinking 2507Alibaba | 78.4 | — | 1,397 | — |
| 151 | qwen3.5 35b A3bAlibaba | 78.3 | — | 1,396 | — |
| 152 | DeepSeek v3.1 TerminusDeepSeek | 78.3 | — | 1,396 | — |
| 153 | Mistral Medium 3.1 2508Mistral | 78.1 | — | 1,395 | — |
| 154 | Amazon Nova Experimental Chat 11 10Amazon | 77.9 | — | 1,394 | — |
| 155 | Ernie 5.0 Preview 1022Baidu | 77.7 | — | 1,393 | — |
| 156 | DeepSeek R1 0528DeepSeek | 77.7 | — | 1,392 | — |
| 157 | MiniMax m2.5MiniMax | 77.7 | — | 1,392 | — |
| 158 | Qwen3 Next 80b A3b ThinkingAlibaba | 77.5 | — | 1,391 | — |
| 159 | Qwen3 235b A22bAlibaba | 77.5 | — | 1,391 | — |
| 160 | Amazon Nova Experimental Chat 10 20Amazon | 77.5 | — | 1,391 | — |
| 161 | Qwen3 235b A22b Non Thinking (Thinking)Alibaba | 77.4 | — | 1,390 | — |
| 162 | Claude Sonnet 4 20250514Anthropic | 77.3 | — | 1,390 | — |
| 163 | MiniMax m2.1 PreviewMiniMax | 77.2 | — | 1,389 | — |
| 164 | Llama 3.3 Nemotron Super 49b v1.5NVIDIA | 77.2 | — | 1,389 | — |
| 165 | Grok 3 Mini (High)xAI | 77.1 | — | 1,389 | — |
| 166 | Kimi K2 Preview 0711Moonshot | 77.0 | — | 1,388 | — |
| 167 | O1 PreviewOpenAI | 76.8 | — | 1,386 | — |
| 168 | GLM 4.5 Airzai | 76.7 | — | 1,386 | — |
| 169 | Claude 3.7 Sonnet (Thinking)Anthropic | 76.7 | — | 1,386 | — |
| 170 | Claude Fable 5.2Anthropic | 76.5 | 88.8 | — | — |
| 171 | Trinity Large ThinkingArcee AI | 76.2 | — | 1,383 | — |
| 172 | GPT 6.1 TerraOpenAI | 76.1 | 88.7 | — | — |
| 173 | O3 (Mini)OpenAI | 76.0 | — | 1,382 | — |
| 174 | Llama 3.1 Nemotron Ultra 253b V1NVIDIA | 75.9 | — | 1,381 | — |
| 175 | GPT Oss 120bOpenAI | 75.9 | — | 1,381 | — |
| 176 | Qwen3 30b A3b Instruct 2507Alibaba | 75.4 | — | 1,378 | — |
| 177 | Qwen3 Coder 480b A35b InstructAlibaba | 75.1 | — | 1,375 | — |
| 178 | Nvidia Nemotron 3.5 Lightning 30b A3b Nvfp4NVIDIA | 75.1 | — | 1,375 | — |
| 179 | Mimo V2 Flash Non Thinking (Thinking)xiaomi | 75.0 | — | 1,375 | — |
| 180 | GPT 4.1 2025 04 14OpenAI | 74.9 | — | 1,375 | — |
| 181 | Intellect 3Prime Intellect | 74.8 | — | 1,373 | — |
| 182 | Mimo V2 Flash (Thinking)xiaomi | 74.6 | — | 1,372 | — |
| 183 | Grok 3 Preview 02 24xAI | 74.4 | — | 1,371 | — |
| 184 | Grok 3 Mini BetaxAI | 74.2 | — | 1,370 | — |
| 185 | Nvidia Nemotron 3 Super 120b A12bNVIDIA | 74.2 | — | 1,370 | — |
| 186 | MiniMax M1MiniMax | 74.2 | — | 1,370 | — |
| 187 | DeepSeek V3 0324DeepSeek | 73.7 | — | 1,366 | — |
| 188 | Claude 3.7 Sonnet 20250219Anthropic | 73.2 | — | 1,364 | — |
| 189 | Gemini 2.5 Flash Lite Preview (Thinking)Google | 73.2 | — | 1,363 | — |
| 190 | Qwq 32bAlibaba | 73.1 | — | 1,363 | — |
| 191 | Mistral Large 4Mistral | 73.1 | 83.9 | 1,459 | — |
| 192 | qwen2.5 (Max)Alibaba | 72.9 | — | 1,362 | — |
| 193 | Trinity Large PreviewOther | 72.9 | — | 1,362 | — |
| 194 | GLM 4.7 Flashzai | 72.9 | — | 1,362 | — |
| 195 | O1 (Mini)OpenAI | 72.9 | — | 1,361 | — |
| 196 | Gemini 2.5 Flash Lite Preview Non Thinking 09 2025 (Thinking)Google | 72.8 | — | 1,361 | — |
| 197 | GLM 4.5vzai | 72.7 | — | 1,360 | — |
| 198 | Step 3StepFun | 72.7 | — | 1,360 | — |
| 199 | Gemini 2.0 Flash 001Google | 72.0 | — | 1,356 | — |
| 200 | MiniMax M2MiniMax | 71.8 | — | 1,354 | — |
| 201 | GPT 4.1 Mini 2025 04 14OpenAI | 71.6 | — | 1,353 | — |
| 202 | Claude 3.5 Sonnet 20241022Anthropic | 71.5 | — | 1,352 | — |
| 203 | Qwen3 30b A3bAlibaba | 71.3 | — | 1,351 | — |
| 204 | GPT 5 Nano (High)OpenAI | 70.8 | — | 1,348 | — |
| 205 | Mistral Medium 3 2505Mistral | 70.7 | — | 1,347 | — |
| 206 | Nvidia Nemotron 3 Nano 30b A3b Bf16NVIDIA | 70.6 | — | 1,347 | — |
| 207 | Ling Flash 2.0ant-group | 70.3 | — | 1,345 | — |
| 208 | Hunyuan Turbos 20250416Tencent | 70.2 | — | 1,344 | — |
| 209 | qwen3.8 Max 0902阿里巴巴 | 70.0 | — | — | 68.4 |
| 210 | Spark x2.6科大讯飞 | 70.0 | — | — | 68.4 |
| 211 | Claude 3.5 Sonnet 20240620Anthropic | 69.9 | — | 1,342 | — |
| 212 | Gemini 1.5 Pro 002Google | 69.5 | — | 1,340 | — |
| 213 | Mistral Small 3.2 2506Mistral | 69.2 | — | 1,338 | — |
| 214 | Ring Flash 2.0InclusionAI | 69.1 | — | 1,337 | — |
| 215 | GPT Oss 20bOpenAI | 68.8 | — | 1,335 | — |
| 216 | Amazon Nova 2 LiteAmazon | 67.8 | — | 1,329 | — |
| 217 | Kimi k3.1 ProMoonshot | 67.5 | 91.1 | — | 63.2 |
| 218 | Gemini 2.0 Flash Lite Preview 02 05Google | 67.5 | — | 1,327 | — |
| 219 | Gemma 3 27b ItGoogle | 66.9 | — | 1,323 | — |
| 220 | Qwen Plus 0125Alibaba | 66.7 | — | 1,322 | — |
| 221 | Llama 3.1 405b Instruct Fp8Meta | 66.4 | — | 1,319 | — |
| 222 | MiniMax M3稀宇科技 | 66.3 | — | 1,425 | 63.2 |
| 223 | Gemma 3 12b ItGoogle | 66.1 | — | 1,318 | — |
| 224 | Granite 4.1 8bIBM | 66.1 | — | 1,317 | — |
| 225 | Llama 4 Maverick 17b 128e InstructMeta | 66.0 | — | 1,317 | — |
| 226 | Llama 3.1 405b Instruct Bf16Meta | 65.8 | — | 1,316 | — |
| 227 | Claude 3 Opus 20240229Anthropic | 65.3 | — | 1,313 | — |
| 228 | qwen3.8 27bAlibaba | 65.2 | 80 | 1,451 | — |
| 229 | Step 2 16k Exp 202412StepFun | 65.2 | — | 1,312 | — |
| 230 | Athene V2 ChatOther | 65.1 | — | 1,311 | — |
| 231 | Olmo 3 32b Thinkallenai | 65.0 | — | 1,310 | — |
| 232 | Command A 03 2025Cohere | 65.0 | — | 1,310 | — |
| 233 | Llama 4 Scout 17b 16e InstructMeta | 64.9 | — | 1,310 | — |
| 234 | DeepSeek V3DeepSeek | 64.9 | — | 1,310 | — |
| 235 | GPT 4o 2024 08 06OpenAI | 64.7 | — | 1,309 | — |
| 236 | Gemini Advanced 0514Google | 64.6 | — | 1,308 | — |
| 237 | Inklingthinky | 64.2 | 78.3 | 1,479 | — |
| 238 | GPT 4o 2024 05 13OpenAI | 64.1 | — | 1,305 | — |
| 239 | Yi LightningOther | 64.0 | — | 1,304 | — |
| 240 | GPT 4 Turbo Preview 1106OpenAI | 63.8 | — | 1,303 | — |
| 241 | qwen2.5 Plus 1127Alibaba | 63.8 | — | 1,303 | — |
| 242 | Olmo 3.1 32b ThinkAllen Institute for AI | 63.7 | — | 1,302 | — |
| 243 | Hunyuan Turbos 20250226Tencent | 63.4 | — | 1,300 | — |
| 244 | Gemini 1.5 Pro 001Google | 63.3 | — | 1,300 | — |
| 245 | GPT 4 Turbo Preview 0125OpenAI | 63.3 | — | 1,299 | — |
| 246 | Mistral Large 4 0Mistral | 63.1 | 85.2 | — | — |
| 247 | Olmo 3.1 32b InstructAllen Institute for AI | 63.1 | — | 1,298 | — |
| 248 | GLM 4 Plus 0111zai | 63.0 | — | 1,298 | — |
| 249 | GPT 4 Turbo 2024 04 09OpenAI | 62.8 | — | 1,296 | — |
| 250 | qwen2.5 72b InstructAlibaba | 62.7 | — | 1,296 | — |
| 251 | Llama 3.3 70b InstructMeta | 62.7 | — | 1,296 | — |
| 252 | Step 1o Turbo 202506StepFun | 62.6 | — | 1,295 | — |
| 253 | Grok 2 2024 08 13xAI | 62.5 | — | 1,294 | — |
| 254 | Hunyuan Large 2025 02 10Tencent | 62.3 | — | 1,293 | — |
| 255 | DeepSeek v2.5 1210DeepSeek | 62.0 | — | 1,291 | — |
| 256 | Qwen Max 0919Alibaba | 62.0 | — | 1,291 | — |
| 257 | Hunyuan Standard 2025 02 10Tencent | 61.8 | — | 1,290 | — |
| 258 | Gemini 1.5 Flash 002Google | 61.6 | — | 1,289 | — |
| 259 | Mistral Large 2 2407Mistral | 61.5 | — | 1,288 | — |
| 260 | Magistral Medium 2506Mistral | 61.4 | — | 1,287 | — |
| 261 | DeepSeek v2.5DeepSeek | 61.4 | — | 1,287 | — |
| 262 | Claude 3.5 Haiku 20241022Anthropic | 61.3 | — | 1,287 | — |
| 263 | GLM 4 Pluszai | 61.3 | — | 1,287 | — |
| 264 | GPT 4 0314OpenAI | 61.0 | — | 1,285 | — |
| 265 | Granite 4.0 H SmallIBM | 60.6 | — | 1,282 | — |
| 266 | Mistral Large 2411Mistral | 60.6 | — | 1,282 | — |
| 267 | Hunyuan Large VisionTencent | 60.3 | — | 1,280 | — |
| 268 | Hunyuan Turbo 0110Tencent | 60.0 | — | 1,279 | — |
| 269 | Llama 3.1 Nemotron 70b InstructNVIDIA | 60.0 | — | 1,278 | — |
| 270 | GPT 4 0613OpenAI | 59.9 | — | 1,278 | — |
| 271 | Mistral Small 3.1 24b Instruct 2503Mistral | 59.7 | — | 1,277 | — |
| 272 | GPT 4o Mini 2024 07 18OpenAI | 59.5 | — | 1,275 | — |
| 273 | Qwen2 72b InstructAlibaba | 59.3 | — | 1,274 | — |
| 274 | Mimo v2.6 Flash小米集团 | 59.2 | — | 1,462 | 57.9 |
| 275 | Step 5 Preview阶跃星辰 | 59.2 | 83.8 | 1,470 | 57.9 |
| 276 | GPT 4.1 Nano 2025 04 14OpenAI | 59.2 | — | 1,273 | — |
| 277 | Grok 2 Mini 2024 08 13xAI | 59.1 | — | 1,272 | — |
| 278 | DeepSeek Coder V2DeepSeek | 59.0 | — | 1,272 | — |
| 279 | Llama 3.1 Nemotron 51b InstructNVIDIA | 59.0 | — | 1,272 | — |
| 280 | qwen2.5 Coder 32b InstructAlibaba | 58.6 | — | 1,269 | — |
| 281 | Llama 3.1 70b InstructMeta | 58.6 | — | 1,269 | — |
| 282 | Amazon Nova Pro 1.0Amazon | 58.5 | — | 1,269 | — |
| 283 | Phi 4Microsoft | 57.9 | — | 1,265 | — |
| 284 | Llama 3.1 Tulu 3 70ballenai | 57.7 | — | 1,263 | — |
| 285 | Athene 70b 0725Other | 57.6 | — | 1,263 | — |
| 286 | Mistral Small 24b Instruct 2501Mistral | 57.4 | — | 1,262 | — |
| 287 | MiniMax m3.1 Flash稀宇科技 | 57.2 | 82.9 | — | 65.8 |
| 288 | Gemini 1.5 Flash 001Google | 57.0 | — | 1,259 | — |
| 289 | Gemma 3n E4b ItGoogle | 57.0 | — | 1,259 | — |
| 290 | Llama 3 70b InstructMeta | 57.0 | — | 1,259 | — |
| 291 | Gemma 3 4b ItGoogle | 56.3 | — | 1,254 | — |
| 292 | Claude 3 Sonnet 20240229Anthropic | 56.2 | — | 1,254 | — |
| 293 | Nemotron 4 340b InstructNVIDIA | 56.0 | — | 1,252 | — |
| 294 | Hunyuan Standard 256kTencent | 55.5 | — | 1,249 | — |
| 295 | Gemma 2 27b ItGoogle | 55.3 | — | 1,248 | — |
| 296 | GLM 4 0520zai | 55.0 | — | 1,246 | — |
| 297 | Reka Core 20240904Other | 55.0 | — | 1,246 | — |
| 298 | Mistral Large 2402Mistral | 54.8 | — | 1,245 | — |
| 299 | Jamba 1.5 LargeOther | 54.8 | — | 1,245 | — |
| 300 | Amazon Nova Lite 1.0Amazon | 54.7 | — | 1,244 | — |
| 301 | GLM 5.3 FlashZhipu | 53.3 | 77.6 | 1,505 | 57.9 |
| 302 | Aya Expanse 32bCohere | 53.1 | — | 1,234 | — |
| 303 | Reka Flash 20240904Other | 53.0 | — | 1,233 | — |
| 304 | Claude 3 Haiku 20240307Anthropic | 52.9 | — | 1,232 | — |
| 305 | Command R+ 08 2024Cohere | 52.8 | — | 1,232 | — |
| 306 | Gemini 1.5 Flash 8b 001Google | 52.5 | — | 1,230 | — |
| 307 | Mixtral 8x22b Instruct v0.1Mistral | 52.3 | — | 1,229 | — |
| 308 | Olmo 2 32b Instruct 0325allenai | 52.0 | — | 1,227 | — |
| 309 | Amazon Nova Micro 1.0Amazon | 51.5 | — | 1,223 | — |
| 310 | qwen1.5 110b ChatAlibaba | 51.2 | — | 1,222 | — |
| 311 | Gemma 2 9b ItGoogle | 51.1 | — | 1,221 | — |
| 312 | Mistral (Medium)Mistral | 51.1 | — | 1,221 | — |
| 313 | Phi 3 Medium 4k InstructMicrosoft | 50.4 | — | 1,216 | — |
| 314 | Command R+Cohere | 50.1 | — | 1,215 | — |
| 315 | Ministral 8b 2410Mistral | 50.0 | — | 1,214 | — |
| 316 | Yi 1.5 34b ChatOther | 49.8 | — | 1,213 | — |
| 317 | Reka Flash 21b Online 20240226Other | 49.8 | — | 1,212 | — |
| 318 | qwen1.5 72b ChatAlibaba | 49.3 | — | 1,209 | — |
| 319 | Qwq 32b PreviewAlibaba | 49.2 | — | 1,209 | — |
| 320 | Gemma 2 9b It SimpoGoogle | 49.1 | — | 1,208 | — |
| 321 | Command R 08 2024Cohere | 49.1 | — | 1,208 | — |
| 322 | internlm2.5 20b ChatOther | 48.9 | — | 1,207 | — |
| 323 | Llama 3.1 Tulu 3 8ballenai | 48.8 | — | 1,206 | — |
| 324 | GPT 3.5 Turbo 1106OpenAI | 48.7 | — | 1,205 | — |
| 325 | Gemini ProGoogle | 48.4 | — | 1,203 | — |
| 326 | GPT 3.5 Turbo 0125OpenAI | 48.2 | — | 1,202 | — |
| 327 | Aya Expanse 8bCohere | 48.1 | — | 1,202 | — |
| 328 | qwen1.5 32b ChatAlibaba | 48.1 | — | 1,201 | — |
| 329 | Reka Flash 21b 20240226Other | 47.8 | — | 1,200 | — |
| 330 | Gemini Pro Dev ApiGoogle | 47.8 | — | 1,199 | — |
| 331 | Granite 3.0 8b InstructIBM | 47.7 | — | 1,199 | — |
| 332 | Granite 3.1 2b InstructIBM | 47.6 | — | 1,198 | — |
| 333 | Zephyr Orpo 141b A35b v0.1Other | 47.4 | — | 1,197 | — |
| 334 | Dbrx Instruct PreviewOther | 47.4 | — | 1,197 | — |
| 335 | Phi 3 Mini 4k Instruct June 2024Microsoft | 46.9 | — | 1,194 | — |
| 336 | Phi 3 Small 8k InstructMicrosoft | 46.9 | — | 1,194 | — |
| 337 | Llama 3 8b InstructMeta | 46.8 | — | 1,193 | — |
| 338 | Mixtral 8x7b Instruct v0.1Mistral | 46.5 | — | 1,191 | — |
| 339 | Granite 3.1 8b InstructIBM | 46.4 | — | 1,191 | — |
| 340 | Llama 3.1 8b InstructMeta | 46.1 | — | 1,188 | — |
| 341 | Jamba 1.5 (Mini)Other | 45.8 | — | 1,187 | — |
| 342 | Mimo v2.6 Pro小米集团 | 44.7 | 79.6 | 1,483 | 50 |
| 343 | Gemma 4 31bGoogle | 44.6 | 68.3 | 1,467 | — |
| 344 | Command RCohere | 44.4 | — | 1,178 | — |
| 345 | Granite 3.0 2b InstructIBM | 43.2 | — | 1,170 | — |
| 346 | qwen1.5 14b ChatAlibaba | 42.8 | — | 1,168 | — |
| 347 | Llama 3.2 3b InstructMeta | 42.5 | — | 1,165 | — |
| 348 | Gemma 2 2b ItGoogle | 42.4 | — | 1,165 | — |
| 349 | Snowflake Arctic InstructOther | 42.3 | — | 1,164 | — |
| 350 | Gemma 1.1 7b ItGoogle | 42.2 | — | 1,163 | — |
| 351 | Openchat 3.5 0106Other | 41.6 | — | 1,159 | — |
| 352 | Wizardlm 70bMicrosoft | 41.3 | — | 1,158 | — |
| 353 | Starling Lm 7b BetaOther | 41.3 | — | 1,158 | — |
| 354 | DeepSeek Llm 67b ChatDeepSeek | 41.1 | — | 1,156 | — |
| 355 | Smollm2 1.7b InstructOther | 40.6 | — | 1,153 | — |
| 356 | Openhermes 2.5 Mistral 7bOther | 40.6 | — | 1,153 | — |
| 357 | Yi 34b ChatOther | 40.2 | — | 1,151 | — |
| 358 | Phi 3 Mini 4k InstructMicrosoft | 40.1 | — | 1,150 | — |
| 359 | Doubao Seed 2.1 Pro 260915ByteDance | 40.0 | — | — | 60.5 |
| 360 | Tulu 2 Dpo 70bOther | 39.3 | — | 1,145 | — |
| 361 | Phi 3 Mini 128k InstructMicrosoft | 38.6 | — | 1,140 | — |
| 362 | Llama 2 70b ChatMeta | 38.1 | — | 1,137 | — |
| 363 | Mistral 7b Instruct v0.2Mistral | 36.6 | — | 1,127 | — |
| 364 | Qwen 14b ChatAlibaba | 36.6 | — | 1,127 | — |
| 365 | Starling Lm 7b AlphaOther | 36.6 | — | 1,127 | — |
| 366 | Openchat 3.5Other | 36.4 | — | 1,126 | — |
| 367 | Dolphin 2.2.1 Mistral 7bOther | 36.4 | — | 1,126 | — |
| 368 | Llama 3.2 1b InstructMeta | 36.0 | — | 1,124 | — |
| 369 | qwen1.5 7b ChatAlibaba | 35.7 | — | 1,121 | — |
| 370 | Gemma 7b ItGoogle | 35.5 | — | 1,121 | — |
| 371 | Palm 2Google | 35.1 | — | 1,118 | — |
| 372 | Vicuna 33bOther | 34.9 | — | 1,116 | — |
| 373 | Llama 2 70b Steerlm ChatNVIDIA | 34.6 | — | 1,114 | — |
| 374 | Gemma 1.1 2b ItGoogle | 34.2 | — | 1,112 | — |
| 375 | Llama 2 13b ChatMeta | 34.0 | — | 1,111 | — |
| 376 | Code Llama 34b InstructMeta | 34.0 | — | 1,110 | — |
| 377 | Solar 10.7b Instruct v1.0upstage | 33.8 | — | 1,109 | — |
| 378 | Mpt 30b ChatOther | 31.8 | — | 1,096 | — |
| 379 | Nous Hermes 2 Mixtral 8x7b DpoOther | 31.3 | — | 1,093 | — |
| 380 | qwen1.5 4b ChatAlibaba | 30.5 | — | 1,088 | — |
| 381 | Llama 2 7b ChatMeta | 30.3 | — | 1,087 | — |
| 382 | Stripedhyena Nous 7bOther | 30.2 | — | 1,086 | — |
| 383 | Hy4 PreviewTencent | 30.0 | — | — | 57.9 |
| 384 | qwen3.8 Flash阿里巴巴 | 30.0 | — | — | 57.9 |
| 385 | Vicuna 13bOther | 29.9 | — | 1,084 | — |
| 386 | Mistral 7b InstructMistral | 29.8 | — | 1,083 | — |
| 387 | Zephyr 7b BetaOther | 29.7 | — | 1,083 | — |
| 388 | Guanaco 33bOther | 29.4 | — | 1,081 | — |
| 389 | Gemma 2b ItGoogle | 28.3 | — | 1,074 | — |
| 390 | Wizardlm 13bMicrosoft | 27.0 | — | 1,065 | — |
| 391 | Smaug Nemotron 3.5 Nvfp4NVIDIA | 25.4 | 75.1 | — | — |
| 392 | Olmo 7b Instructallenai | 25.2 | — | 1,054 | — |
| 393 | Vicuna 7bOther | 24.4 | — | 1,049 | — |
| 394 | Chatglm3 6bZhipu | 23.5 | — | 1,043 | — |
| 395 | Nemotron Super Vl 3.5NVIDIA | 23.5 | 74.6 | — | — |
| 396 | Muse Spark OpenMeta | 20.1 | 73.7 | — | — |
| 397 | Longcat 2.5 Preview美团 | 20.0 | — | — | 55.3 |
| 398 | Gpt4all 13b SnoozyOther | 16.9 | — | 1,000 | — |
| 399 | Alpaca 13bOther | 16.3 | — | 997 | — |
| 400 | Mpt 7b ChatOther | 15.0 | — | 988 | — |
| 401 | Rwkv 4 Raven 14bOther | 14.6 | — | 985 | — |
| 402 | Koala 13bOther | 13.8 | — | 981 | — |
| 403 | Chatglm 6bZhipu | 13.4 | — | 978 | — |
| 404 | Nemotron Super Vl 3.5 Nvfp4NVIDIA | 12.7 | 71.7 | — | — |
| 405 | Chatglm2 6bZhipu | 12.7 | — | 973 | — |
| 406 | Openassistant Pythia 12bOther | 11.1 | — | 963 | — |
| 407 | Dolly 2.0 12bOther | 9.9 | — | 955 | — |
| 408 | Llama 13bMeta | 5.1 | — | 924 | — |
| 409 | Fastchat T5 3bOther | 4.7 | — | 921 | — |
| 410 | Stablelm Tuned Alpha 7bOther | 0 | — | 891 | — |