| 1 | — | OGPT-5.2 (xhigh)ClosedOpenAI | 50.6 | — | — | — |
| 2 | — | AClaude Opus 4.5 (Reasoning)ClosedAnthropic | 49.1 | — | — | — |
| 3 | — | GGemini 3 Pro Preview (high)ClosedGoogle | 47.9 | — | — | — |
| 4 | — | OGPT-5.1 (high)ClosedOpenAI | 47.0 | — | — | — |
| 5 | — | GGemini 3 Flash Preview (Reasoning)ClosedGoogle | 45.8 | — | — | — |
| 6 | — | OGPT-5.2 (medium)ClosedOpenAI | 45.4 | — | — | — |
| 7 | — | OGPT-5 (high)ClosedOpenAI | 44.1 | — | — | — |
| 8 | — | OGPT-5 Codex (high)ClosedOpenAI | 44.0 | — | — | — |
| 9 | — | AClaude Opus 4.5 (Non-reasoning)ClosedAnthropic | 42.5 | — | — | — |
| 10 | — | AClaude 4.5 Sonnet (Reasoning)ClosedAnthropic | 42.4 | — | — | — |
| 11 | — | OGPT-5 (medium)ClosedOpenAI | 41.9 | — | — | — |
| 12 | — | ZGLM-4.7 (Reasoning)OpenZ AI | 41.7 | — | — | — |
| 13 | — | OGPT-5.1 Codex (high)ClosedOpenAI | 41.6 | — | — | — |
| 14 | — | XGrok 4ClosedxAI | 41.4 | — | — | — |
| 15 | — | DDeepSeek V3.2 (Reasoning)OpenDeepSeek | 41.2 | — | — | — |
| 16 | — | OGPT-5 mini (high)ClosedOpenAI | 40.6 | — | — | — |
| 17 | — | GGemini 3 Pro Preview (low)ClosedGoogle | 40.6 | — | — | — |
| 18 | — | KKimi K2 ThinkingOpenKimi | 40.3 | — | — | — |
| 19 | — | MMiniMax-M2.1OpenMiniMax | 39.4 | — | — | — |
| 20 | — | XMiMo-V2-Flash (Reasoning)OpenXiaomi | 39.1 | — | — | — |
| 21 | — | OGPT-5 (low)ClosedOpenAI | 38.7 | — | — | — |
| 22 | — | OGPT-5 mini (medium)ClosedOpenAI | 38.6 | — | — | — |
| 23 | — | AClaude 4 Sonnet (Reasoning)ClosedAnthropic | 38.3 | — | — | — |
| 24 | — | XGrok 4.1 Fast (Reasoning)ClosedxAI | 38.2 | — | — | — |
| 25 | — | OGPT-5.1 Codex mini (high)ClosedOpenAI | 38.0 | — | — | — |
| 26 | — | AClaude 4.5 Haiku (Reasoning)ClosedAnthropic | 36.6 | — | — | — |
| 27 | — | AClaude 4.5 Sonnet (Non-reasoning)ClosedAnthropic | 36.6 | — | — | — |
| 28 | — | KKAT-Coder-Pro V1ClosedKwaiKAT | 36.1 | — | — | — |
| 29 | — | MMiniMax-M2OpenMiniMax | 35.7 | — | — | — |
| 30 | — | ANova 2.0 Pro Preview (medium)ClosedAmazon | 35.3 | — | — | — |
| 31 | — | GGemini 3 Flash Preview (Non-reasoning)ClosedGoogle | 34.8 | — | — | — |
| 32 | — | XGrok 4 Fast (Reasoning)ClosedxAI | 34.6 | — | — | — |
| 33 | — | AClaude 3.7 Sonnet (Reasoning)ClosedAnthropic | 34.4 | — | — | — |
| 34 | — | GGemini 2.5 ProClosedGoogle | 34.1 | — | — | — |
| 35 | — | ZGLM-4.7 (Non-reasoning)OpenZ AI | 33.8 | — | — | — |
| 36 | — | DDeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek | 33.5 | — | — | — |
| 37 | — | BDoubao Seed CodeClosedByteDance Seed | 33.2 | — | — | — |
| 38 | — | OGPT-5.2 (Non-reasoning)ClosedOpenAI | 33.1 | — | — | — |
| 39 | — | Oo4-mini (high)ClosedOpenAI | 32.9 | — | — | — |
| 40 | — | Ogpt-oss-120B (high)OpenOpenAI | 32.9 | — | — | — |
| 41 | — | AClaude 4 Sonnet (Non-reasoning)ClosedAnthropic | 32.7 | — | — | — |
| 42 | — | DDeepSeek V3.2 Exp (Reasoning)OpenDeepSeek | 32.5 | — | — | — |
| 43 | — | XGrok 3 mini Reasoning (high)ClosedxAI | 32.4 | — | — | — |
| 44 | — | AQwen3 Max ThinkingClosedAlibaba | 32.3 | — | — | — |
| 45 | — | ZGLM-4.6 (Reasoning)OpenZ AI | 32.2 | — | — | — |
| 46 | — | ANova 2.0 Pro Preview (low)ClosedAmazon | 32.2 | — | — | — |
| 47 | — | LK-EXAONE (Reasoning)OpenLG AI Research | 31.9 | — | — | — |
| 48 | — | DDeepSeek V3.2 (Non-reasoning)OpenDeepSeek | 31.9 | — | — | — |
| 49 | — | AQwen3 MaxClosedAlibaba | 31.0 | — | — | — |
| 50 | — | GGemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle | 30.8 | — | — | — |
| 51 | — | AClaude 3.7 Sonnet (Non-reasoning)ClosedAnthropic | 30.6 | — | — | — |
| 52 | — | AClaude 4.5 Haiku (Non-reasoning)ClosedAnthropic | 30.5 | — | — | — |
| 53 | — | XMiMo-V2-Flash (Non-reasoning)OpenXiaomi | 30.1 | — | — | — |
| 54 | — | ANova 2.0 Lite (medium)ClosedAmazon | 29.9 | — | — | — |
| 55 | — | ZGLM-4.6 (Non-reasoning)OpenZ AI | 29.8 | — | — | — |
| 56 | — | AQwen3 235B A22B 2507 (Reasoning)OpenAlibaba | 29.4 | — | — | — |
| 57 | — | DDeepSeek V3.2 SpecialeOpenDeepSeek | 29.0 | — | — | — |
| 58 | — | BERNIE 5.0 Thinking PreviewClosedBaidu | 28.9 | — | — | — |
| 59 | — | KKimi K2 0905OpenKimi | 28.0 | — | — | — |
| 60 | — | DDeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek | 28.0 | — | — | — |
| 61 | — | DDeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek | 28.0 | — | — | — |
| 62 | — | DDeepSeek V3.1 (Reasoning)OpenDeepSeek | 27.9 | — | — | — |
| 63 | — | ANova 2.0 Omni (medium)ClosedAmazon | 27.9 | — | — | — |
| 64 | — | SApriel-v1.6-15B-ThinkerOpenServiceNow | 27.8 | — | — | — |
| 65 | — | DDeepSeek V3.1 (Non-reasoning)OpenDeepSeek | 27.7 | — | — | — |
| 66 | — | AQwen3 VL 235B A22B (Reasoning)OpenAlibaba | 27.5 | — | — | — |
| 67 | — | MMagistral Medium 1.2ClosedMistral | 27.5 | — | — | — |
| 68 | — | GGemini 2.5 Flash (Reasoning)ClosedGoogle | 27.2 | — | — | — |
| 69 | — | OGPT-5.1 (Non-reasoning)ClosedOpenAI | 27.2 | — | — | — |
| 70 | — | DDeepSeek R1 0528 (May '25)OpenDeepSeek | 27.1 | — | — | — |
| 71 | — | ZGLM-4.5 (Reasoning)OpenZ AI | 26.8 | — | — | — |
| 72 | — | OGPT-5 nano (high)ClosedOpenAI | 26.7 | — | — | — |
| 73 | — | AQwen3 Next 80B A3B (Reasoning)OpenAlibaba | 26.5 | — | — | — |
| 74 | — | OGPT-5 nano (medium)ClosedOpenAI | 25.8 | — | — | — |
| 75 | — | OGPT-4.1ClosedOpenAI | 25.8 | — | — | — |
| 76 | — | GGemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle | 25.6 | — | — | — |
| 77 | — | XGrok 3ClosedxAI | 25.2 | — | — | — |
| 78 | — | BSeed-OSS-36B-InstructOpenByteDance Seed | 25.0 | — | — | — |
| 79 | — | ANova 2.0 Lite (low)ClosedAmazon | 25.0 | — | — | — |
| 80 | — | AQwen3 Coder 480B A35B InstructOpenAlibaba | 24.8 | — | — | — |
| 81 | — | NNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA | 24.7 | — | — | — |
| 82 | — | Ogpt-oss-20B (high)OpenOpenAI | 24.7 | — | — | — |
| 83 | — | AQwen3 235B A22B 2507 InstructOpenAlibaba | 24.6 | — | — | — |
| 84 | — | OGPT-5 (minimal)ClosedOpenAI | 24.5 | — | — | — |
| 85 | — | MMiniMax M1 80kOpenMiniMax | 24.3 | — | — | — |
| 86 | — | ANova 2.0 Omni (low)ClosedAmazon | 24.1 | — | — | — |
| 87 | — | NHyperCLOVA X SEED Think (32B)OpenNaver | 24.0 | — | — | — |
| 88 | — | ZGLM-4.6V (Reasoning)OpenZ AI | 23.8 | — | — | — |
| 89 | — | Ogpt-oss-120B (low)OpenOpenAI | 23.8 | — | — | — |
| 90 | — | ZGLM-4.5-AirOpenZ AI | 23.6 | — | — | — |
| 91 | — | XGrok 4.1 Fast (Non-reasoning)ClosedxAI | 23.6 | — | — | — |
| 92 | — | ANova 2.0 Pro Preview (Non-reasoning)ClosedAmazon | 23.5 | — | — | — |
| 93 | — | KMi:dm K 2.5 ProOpenKorea Telecom | 23.2 | — | — | — |
| 94 | — | LK-EXAONE (Non-reasoning)OpenLG AI Research | 23.2 | — | — | — |
| 95 | — | OGPT-4.1 miniClosedOpenAI | 22.9 | — | — | — |
| 96 | — | AQwen3 30B A3B 2507 (Reasoning)OpenAlibaba | 22.8 | — | — | — |
| 97 | — | XGrok 4 Fast (Non-reasoning)ClosedxAI | 22.8 | — | — | — |
| 98 | — | DDeepSeek V3 0324OpenDeepSeek | 22.6 | — | — | — |
| 99 | — | MMistral Large 3OpenMistral | 22.5 | — | — | — |
| 100 | — | GGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle | 22.3 | — | — | — |
| 101 | — | PINTELLECT-3OpenPrime Intellect | 22.2 | — | — | — |
| 102 | — | MDevstral 2OpenMistral | 21.7 | — | — | — |
| 103 | — | OGPT-5 mini (minimal)ClosedOpenAI | 21.5 | — | — | — |
| 104 | — | Ogpt-oss-20B (low)OpenOpenAI | 21.2 | — | — | — |
| 105 | — | MMistral Medium 3.1ClosedMistral | 21.1 | — | — | — |
| 106 | — | MK2-V2 (high)OpenMBZUAI Institute of Foundation Models | 21.1 | — | — | — |
| 107 | — | GGemini 2.5 Flash (Non-reasoning)ClosedGoogle | 20.9 | — | — | — |
| 108 | — | AQwen3 VL 235B A22B InstructOpenAlibaba | 20.8 | — | — | — |
| 109 | — | AQwen3 Next 80B A3B InstructOpenAlibaba | 20.3 | — | — | — |
| 110 | — | AQwen3 Coder 30B A3B InstructOpenAlibaba | 20.2 | — | — | — |
| 111 | — | GGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle | 20.1 | — | — | — |
| 112 | — | AQwen3 235B A22B (Reasoning)OpenAlibaba | 19.9 | — | — | — |
| 113 | — | ILing-1TOpenInclusionAI | 19.7 | — | — | — |
| 113 | — | AQwen3 VL 30B A3B (Reasoning)OpenAlibaba | 19.7 | — | — | — |
| 115 | — | NLlama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA | 19.4 | — | — | — |
| 116 | — | ANova PremierClosedAmazon | 19.2 | — | — | — |
| 117 | — | MK2-V2 (medium)OpenMBZUAI Institute of Foundation Models | 19.2 | — | — | — |
| 118 | — | MDevstral Small 2OpenMistral | 19.1 | — | — | — |
| 119 | — | GGemini 2.0 Flash (Feb '25)ClosedGoogle | 18.9 | — | — | — |
| 120 | — | MLlama 4 MaverickOpenMeta | 18.9 | — | — | — |
| 121 | — | ANova 2.0 Lite (Non-reasoning)ClosedAmazon | 18.8 | — | — | — |
| 122 | — | MDevstral MediumClosedMistral | 18.8 | — | — | — |
| 123 | — | AQwen3 4B 2507 (Reasoning)OpenAlibaba | 18.8 | — | — | — |
| 124 | — | DDeepSeek R1 (Jan '25)OpenDeepSeek | 18.7 | — | — | — |
| 125 | — | GGemini 2.5 Flash-Lite (Reasoning)ClosedGoogle | 17.9 | — | — | — |
| 126 | — | MLlama 3.1 Instruct 405BOpenMeta | 17.5 | — | — | — |
| 127 | — | ZGLM-4.6V (Non-reasoning)OpenZ AI | 17.4 | — | — | — |
| 128 | — | AQwen3 235B A22B (Non-reasoning)OpenAlibaba | 17.3 | — | — | — |
| 129 | — | ANova 2.0 Omni (Non-reasoning)ClosedAmazon | 17.2 | — | — | — |
| 130 | — | AQwen3 VL 32B InstructOpenAlibaba | 17.1 | — | — | — |
| 131 | — | AQwen3 32B (Reasoning)OpenAlibaba | 17.1 | — | — | — |
| 132 | — | AQwen3 VL 8B (Reasoning)OpenAlibaba | 17.0 | — | — | — |
| 133 | — | DDeepSeek V3 (Dec '24)OpenDeepSeek | 17.0 | — | — | — |
| 134 | — | LEXAONE 4.0 32B (Reasoning)OpenLG AI Research | 17.0 | — | — | — |
| 135 | — | AQwen3 14B (Reasoning)OpenAlibaba | 16.8 | — | — | — |
| 136 | — | AQwen3 VL 30B A3B InstructOpenAlibaba | 16.3 | — | — | — |
| 137 | — | MMinistral 14B (Dec '25)OpenMistral | 16.3 | — | — | — |
| 138 | — | TFalcon-H1R-7BOpenTII UAE | 16.2 | — | — | — |
| 139 | — | AQwen3 30B A3B (Reasoning)OpenAlibaba | 15.8 | — | — | — |
| 140 | — | AQwen3 Omni 30B A3B (Reasoning)OpenAlibaba | 15.8 | — | — | — |
| 141 | — | MDevstral Small (Jul '25)OpenMistral | 15.7 | — | — | — |
| 142 | — | USolar Pro 2 (Reasoning)ClosedUpstage | 15.5 | — | — | — |
| 143 | — | NNVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA | 15.5 | — | — | — |
| 144 | — | NLlama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA | 15.4 | — | — | — |
| 144 | — | AQwen3 30B A3B 2507 InstructOpenAlibaba | 15.4 | — | — | — |
| 146 | — | MMistral Small 3.2OpenMistral | 15.3 | — | — | — |
| 147 | — | MK2-V2 (low)OpenMBZUAI Institute of Foundation Models | 15.3 | — | — | — |
| 148 | — | NNVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA | 15.1 | — | — | — |
| 149 | — | MMinistral 8B (Dec '25)OpenMistral | 15.1 | — | — | — |
| 150 | — | MLlama 3.3 Instruct 70BOpenMeta | 15.1 | — | — | — |
| 151 | — | AQwen3 VL 8B InstructOpenAlibaba | 14.6 | — | — | — |
| 152 | — | AOlmo 3.1 32B ThinkOpenAllen Institute for AI | 14.2 | — | — | — |
| 152 | — | USolar Pro 2 (Non-reasoning)ClosedUpstage | 14.2 | — | — | — |
| 154 | — | MLlama 4 ScoutOpenMeta | 14.0 | — | — | — |
| 155 | — | NLlama 3.1 Nemotron Instruct 70BOpenNVIDIA | 14.0 | — | — | — |
| 156 | — | OGPT-5 nano (minimal)ClosedOpenAI | 14.0 | — | — | — |
| 157 | — | NNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA | 13.9 | — | — | — |
| 158 | — | NNVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA | 13.8 | — | — | — |
| 159 | — | CCommand AOpenCohere | 13.7 | — | — | — |
| 160 | — | OGPT-4.1 nanoClosedOpenAI | 13.4 | — | — | — |
| 161 | — | AQwen3 14B (Non-reasoning)OpenAlibaba | 13.4 | — | — | — |
| 162 | — | ZGLM-4.5V (Non-reasoning)OpenZ AI | 13.2 | — | — | — |
| 163 | — | AQwen3 4B 2507 InstructOpenAlibaba | 13.1 | — | — | — |
| 164 | — | GGemini 2.5 Flash-Lite (Non-reasoning)ClosedGoogle | 13.0 | — | — | — |
| 165 | — | ANova LiteClosedAmazon | 12.5 | — | — | — |
| 166 | — | AQwen3 30B A3B (Non-reasoning)OpenAlibaba | 12.4 | — | — | — |
| 167 | — | MLlama 3.1 Instruct 8BOpenMeta | 12.2 | — | — | — |
| 168 | — | MMinistral 3B (Dec '25)OpenMistral | 12.1 | — | — | — |
| 169 | — | LEXAONE 4.0 32B (Non-reasoning)OpenLG AI Research | 12.0 | — | — | — |
| 170 | — | IGranite 4.0 H SmallOpenIBM | 11.5 | — | — | — |
| 171 | — | AQwen3 8B (Non-reasoning)OpenAlibaba | 10.8 | — | — | — |
| 172 | — | AQwen3 Omni 30B A3B InstructOpenAlibaba | 10.7 | — | — | — |
| 173 | — | GGemma 3 27B InstructOpenGoogle | 10.5 | — | — | — |
| 174 | — | NNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA | 10.4 | — | — | — |
| 175 | — | AJamba 1.7 LargeOpenAI21 Labs | 9.7 | — | — | — |
| 176 | — | GGemma 3 12B InstructOpenGoogle | 9.4 | — | — | — |
| 177 | — | LExaone 4.0 1.2B (Reasoning)OpenLG AI Research | 8.6 | — | — | — |
| 178 | — | LExaone 4.0 1.2B (Non-reasoning)OpenLG AI Research | 8.6 | — | — | — |
| 179 | — | IGranite 4.0 H 1BOpenIBM | 8.4 | — | — | — |
| 180 | — | AOlmo 3 7B InstructOpenAllen Institute for AI | 8.2 | — | — | — |
| 181 | — | AJamba 1.7 MiniOpenAI21 Labs | 7.9 | — | — | — |
| 182 | — | LLFM2 2.6BOpenLiquid AI | 7.9 | — | — | — |
| 183 | — | IGranite 4.0 1BOpenIBM | 7.7 | — | — | — |
| 184 | — | LLFM2 8B A1BOpenLiquid AI | 7.3 | — | — | — |
| 185 | — | IGranite 4.0 350MOpenIBM | 7.2 | — | — | — |
| 186 | — | LLFM2 1.2BOpenLiquid AI | 6.8 | — | — | — |
| 187 | — | AQwen3 1.7B (Non-reasoning)OpenAlibaba | 6.8 | — | — | — |
| 188 | — | GGemma 3 4B InstructOpenGoogle | 6.6 | — | — | — |
| 189 | — | GGemma 3n E4B InstructOpenGoogle | 6.3 | — | — | — |
| 190 | — | AQwen3 0.6B (Non-reasoning)OpenAlibaba | 6.1 | — | — | — |
| 191 | — | IGranite 4.0 H 350MOpenIBM | 6.0 | — | — | — |
