| 1 | — | GGemini 3.1 Pro PreviewClosedGoogle | 57.2 | $4.5 | 129 | 29 s |
| 2 | — | OGPT-5.4 (xhigh)ClosedOpenAI | 56.8 | $5.6 | 72 | 206 s |
| 3 | — | OGPT-5.3 Codex (xhigh)ClosedOpenAI | 53.6 | $4.8 | 81 | 116 s |
| 4 | — | AClaude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 53.0 | $10 | 40 | 17 s |
| 5 | — | MMuse SparkClosedMeta | 52.2 | — | — | — |
| 6 | — | AClaude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic | 51.7 | $6.0 | 48 | 94 s |
| 7 | — | OGPT-5.2 (xhigh)ClosedOpenAI | 51.3 | $4.8 | 69 | 173 s |
| 8 | — | AQwen3.6 PlusClosedAlibaba | 50.0 | $1.1 | 53 | 2.8 s |
| 9 | — | AClaude Opus 4.5 (Reasoning)ClosedAnthropic | 49.7 | $10 | 45 | 14 s |
| 10 | ▲ 1 | XGrok 4.20 0309 v2 (Reasoning)ClosedxAI | 49.3 | $3.0 | 162 | 13 s |
| 11 | ▲ 1 | XMiMo-V2-ProClosedXiaomi | 49.2 | $1.5 | 66 | 3.0 s |
| 12 | ▲ 1 | OGPT-5.2 Codex (xhigh)ClosedOpenAI | 49.0 | $4.8 | 121 | 125 s |
| 13 | ▲ 1 | OGPT-5.4 mini (xhigh)ClosedOpenAI | 48.9 | $1.7 | 149 | 9.8 s |
| 14 | ▲ 1 | XGrok 4.20 0309 (Reasoning)ClosedxAI | 48.5 | $3.0 | 155 | 17 s |
| 15 | ▲ 1 | GGemini 3 Pro Preview (high)ClosedGoogle | 48.4 | $4.5 | 130 | 33 s |
| 16 | ▲ 1 | OGPT-5.1 (high)ClosedOpenAI | 47.7 | $3.4 | 91 | 30 s |
| 17 | ▲ 1 | ZGLM-5-TurboClosedZ AI | 46.8 | — | — | — |
| 18 | ▲ 1 | OGPT-5.2 (medium)ClosedOpenAI | 46.6 | $4.8 | — | — |
| 19 | ▲ 1 | AClaude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic | 46.5 | $10 | 37 | 1.7 s |
| 20 | ▲ 1 | GGemini 3 Flash Preview (Reasoning)ClosedGoogle | 46.4 | $1.1 | 149 | 7.3 s |
| 21 | ▲ 1 | XMiMo-V2-Omni-0327ClosedXiaomi | 44.9 | — | — | — |
| 22 | ▲ 1 | OGPT-5 (high)ClosedOpenAI | 44.6 | $3.4 | 85 | 84 s |
| 22 | ▲ 1 | OGPT-5 Codex (high)ClosedOpenAI | 44.6 | $3.4 | 168 | 10 s |
| 24 | ▲ 1 | AClaude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic | 44.4 | $6.0 | 44 | 1.3 s |
| 25 | ▲ 1 | OGPT-5.4 nano (xhigh)ClosedOpenAI | 44.0 | $0.46 | 156 | 4.4 s |
| 26 | ▲ 1 | XMiMo-V2-OmniClosedXiaomi | 43.4 | — | — | — |
| 27 | ▲ 1 | OGPT-5.1 Codex (high)ClosedOpenAI | 43.1 | $3.4 | 163 | 8.2 s |
| 28 | ▲ 1 | AClaude Opus 4.5 (Non-reasoning)ClosedAnthropic | 43.1 | $10 | 45 | 1.5 s |
| 29 | ▲ 1 | AClaude 4.5 Sonnet (Reasoning)ClosedAnthropic | 43.0 | $6.0 | 40 | 9.9 s |
| 30 | ▲ 1 | ZGLM 5V Turbo (Reasoning)ClosedZ AI | 42.9 | — | — | — |
| 31 | ▲ 1 | AClaude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic | 42.6 | $6.0 | 45 | 1.3 s |
| 32 | ▲ 1 | OGPT-5 (medium)ClosedOpenAI | 42.0 | $3.4 | 76 | 44 s |
| 33 | ▲ 1 | AClaude 4.1 Opus (Reasoning)ClosedAnthropic | 42.0 | $30 | 30 | 9.9 s |
| 34 | ▲ 1 | XGrok 4ClosedxAI | 41.5 | $6.0 | 55 | 11 s |
| 35 | ▲ 1 | GGemini 3 Pro Preview (low)ClosedGoogle | 41.3 | $4.5 | — | — |
| 36 | ▲ 1 | OGPT-5 mini (high)ClosedOpenAI | 41.2 | $0.69 | 77 | 95 s |
| 37 | ▲ 1 | Oo3-proClosedOpenAI | 40.7 | $35 | 27 | 128 s |
| 38 | ▲ 1 | AQwen3 Max ThinkingClosedAlibaba | 39.9 | $2.4 | 37 | 4.1 s |
| 39 | ▲ 1 | OGPT-5 (low)ClosedOpenAI | 39.2 | $3.4 | 71 | 6.3 s |
| 40 | ▲ 1 | AClaude 4 Opus (Reasoning)ClosedAnthropic | 39.0 | $30 | 30 | 7.9 s |
| 41 | ▲ 1 | OGPT-5 mini (medium)ClosedOpenAI | 38.9 | $0.69 | 72 | 16 s |
| 42 | ▲ 1 | AClaude 4 Sonnet (Reasoning)ClosedAnthropic | 38.7 | $6.0 | 43 | 11 s |
| 43 | ▲ 1 | OGPT-5.1 Codex mini (high)ClosedOpenAI | 38.6 | $0.69 | 200 | 7.0 s |
| 43 | ▲ 1 | AQwen3.5 Omni PlusClosedAlibaba | 38.6 | $1.5 | 47 | 2.5 s |
| 45 | ▲ 1 | XGrok 4.1 Fast (Reasoning)ClosedxAI | 38.6 | $0.28 | 150 | 7.6 s |
| 46 | New | SStep 3.5 Flash 2603ClosedStepFun | 38.5 | $0.000 | 196 | 0.9 s |
| 47 | — | Oo3ClosedOpenAI | 38.4 | $3.5 | 89 | 8.4 s |
| 48 | — | OGPT-5.4 nano (medium)ClosedOpenAI | 38.1 | $0.46 | 154 | 3.8 s |
| 49 | — | OGPT-5.4 mini (medium)ClosedOpenAI | 37.7 | $1.7 | 152 | 14 s |
| 50 | — | AClaude 4.5 Sonnet (Non-reasoning)ClosedAnthropic | 37.1 | $6.0 | 38 | 1.4 s |
| 51 | — | AClaude 4.5 Haiku (Reasoning)ClosedAnthropic | 37.1 | $2.0 | 88 | 10 s |
| 52 | — | AClaude 4.1 Opus (Non-reasoning)ClosedAnthropic | 36.0 | $30 | 29 | 1.7 s |
| 53 | — | ANova 2.0 Pro Preview (medium)ClosedAmazon | 35.7 | $3.4 | 128 | 12 s |
| 54 | — | OGPT-5.4 (Non-reasoning)ClosedOpenAI | 35.4 | $5.6 | 54 | 0.8 s |
| 55 | — | XGrok 4 Fast (Reasoning)ClosedxAI | 35.1 | $0.28 | 201 | 3.0 s |
| 56 | — | GGemini 3 Flash Preview (Non-reasoning)ClosedGoogle | 35.1 | $1.1 | 151 | 1.2 s |
| 57 | — | AClaude 3.7 Sonnet (Reasoning)ClosedAnthropic | 34.7 | $6.0 | — | — |
| 58 | — | GGemini 2.5 ProClosedGoogle | 34.6 | $3.4 | 118 | 25 s |
| 59 | — | ANova 2.0 Lite (high)ClosedAmazon | 34.5 | $0.85 | 145 | 19 s |
| 60 | — | OGPT-5.2 (Non-reasoning)ClosedOpenAI | 33.6 | $4.8 | 58 | 0.9 s |
| 61 | — | BDoubao Seed CodeClosedByteDance Seed | 33.5 | — | — | — |
| 61 | — | GGemini 3.1 Flash-Lite PreviewClosedGoogle | 33.5 | $0.56 | 236 | 7.1 s |
| 63 | — | Oo4-mini (high)ClosedOpenAI | 33.1 | $1.9 | 128 | 27 s |
| 64 | — | AClaude 4 Opus (Non-reasoning)ClosedAnthropic | 33.0 | $30 | 30 | 1.5 s |
| 64 | — | AClaude 4 Sonnet (Non-reasoning)ClosedAnthropic | 33.0 | $6.0 | 39 | 1.1 s |
| 66 | — | IMercury 2ClosedInception | 32.8 | $0.38 | 625 | 4.4 s |
| 67 | — | AQwen3 Max Thinking (Preview)ClosedAlibaba | 32.5 | $2.4 | 41 | 4.2 s |
| 68 | — | XGrok 3 mini Reasoning (high)ClosedxAI | 32.1 | $0.35 | 190 | 0.6 s |
| 69 | — | ANova 2.0 Pro Preview (low)ClosedAmazon | 31.9 | $3.4 | 132 | 11 s |
| 70 | — | AQwen3 MaxClosedAlibaba | 31.4 | $2.4 | 59 | 3.1 s |
| 71 | — | GGemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle | 31.1 | — | — | — |
| 72 | — | AClaude 4.5 Haiku (Non-reasoning)ClosedAnthropic | 31.1 | $2.0 | 88 | 0.8 s |
| 73 | — | AClaude 3.7 Sonnet (Non-reasoning)ClosedAnthropic | 30.8 | $6.0 | — | — |
| 74 | — | Oo1ClosedOpenAI | 30.8 | $26 | 87 | 40 s |
| 75 | — | GGemini 2.5 Pro Preview (Mar' 25)ClosedGoogle | 30.3 | — | — | — |
| 76 | — | ANova 2.0 Lite (medium)ClosedAmazon | 29.7 | $0.85 | 152 | 18 s |
| 77 | — | XGrok 4.20 0309 (Non-reasoning)ClosedxAI | 29.7 | $3.0 | 133 | 0.6 s |
| 78 | — | GGemini 2.5 Pro Preview (May' 25)ClosedGoogle | 29.5 | $3.4 | — | — |
| 79 | — | BERNIE 5.0 Thinking PreviewClosedBaidu | 29.1 | — | — | — |
| 80 | — | XGrok 4.20 0309 v2 (Non-reasoning)ClosedxAI | 29.0 | $3.0 | 149 | 0.6 s |
| 81 | — | XGrok Code Fast 1ClosedxAI | 28.7 | $0.53 | 140 | 4.5 s |
| 82 | — | ANova 2.0 Omni (medium)ClosedAmazon | 28.0 | $0.85 | — | — |
| 83 | — | OGPT-5.1 (Non-reasoning)ClosedOpenAI | 27.4 | $3.4 | 83 | 1.3 s |
| 84 | — | MMagistral Medium 1.2ClosedMistral | 27.1 | $2.8 | 73 | 1.6 s |
| 85 | — | GGemini 2.5 Flash (Reasoning)ClosedGoogle | 27.0 | $0.85 | 200 | 23 s |
| 86 | — | OGPT-5 nano (high)ClosedOpenAI | 26.8 | $0.14 | 135 | 64 s |
| 87 | — | OGPT-4.1ClosedOpenAI | 26.3 | $3.5 | 84 | 1.1 s |
| 88 | — | AQwen3 Max (Preview)ClosedAlibaba | 26.1 | $2.4 | 46 | 4.2 s |
| 89 | — | OGPT-5 nano (medium)ClosedOpenAI | 25.9 | $0.14 | 121 | 48 s |
| 90 | — | AQwen3.5 Omni FlashClosedAlibaba | 25.9 | $0.28 | 165 | 2.0 s |
| 90 | — | USolar Pro 3ClosedUpstage | 25.9 | — | — | — |
| 92 | — | Oo3-miniClosedOpenAI | 25.9 | $1.9 | 142 | 8.4 s |
| 93 | — | Oo1-proClosedOpenAI | 25.8 | $263 | — | — |
| 94 | — | GGemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle | 25.7 | — | — | — |
| 95 | New | CJT-MINIClosedChina Mobile | 25.4 | — | — | — |
| 96 | ▼ 1 | Oo3-mini (high)ClosedOpenAI | 25.2 | $1.9 | 139 | 39 s |
| 97 | ▼ 1 | XGrok 3ClosedxAI | 25.2 | $6.0 | 67 | 1.4 s |
| 98 | ▼ 1 | PSonar Reasoning ProClosedPerplexity | 24.6 | — | — | — |
| 99 | ▼ 1 | ANova 2.0 Lite (low)ClosedAmazon | 24.6 | $0.85 | 168 | 9.3 s |
| 100 | ▼ 1 | OGPT-5.4 nano (Non-Reasoning)ClosedOpenAI | 24.4 | $0.46 | 157 | 0.6 s |
| 101 | ▼ 1 | GGemini 2.5 Flash Preview (Reasoning)ClosedGoogle | 24.3 | — | — | — |
| 102 | ▼ 1 | OGPT-5 (minimal)ClosedOpenAI | 23.9 | $3.4 | 69 | 1.6 s |
| 103 | ▼ 1 | Oo1-previewClosedOpenAI | 23.7 | $29 | — | — |
| 104 | ▼ 1 | XGrok 4.1 Fast (Non-reasoning)ClosedxAI | 23.6 | $0.28 | 148 | 0.6 s |
| 105 | ▼ 1 | OGPT-5.4 mini (Non-Reasoning)ClosedOpenAI | 23.3 | $1.7 | 141 | 0.6 s |
| 106 | ▼ 1 | ANova 2.0 Omni (low)ClosedAmazon | 23.2 | $0.85 | — | — |
| 107 | ▼ 1 | XGrok 4 Fast (Non-reasoning)ClosedxAI | 23.1 | $0.28 | 196 | 0.6 s |
| 108 | ▼ 1 | KMi:dm K 2.5 ProClosedKorea Telecom | 23.1 | — | — | — |
| 108 | ▼ 1 | ANova 2.0 Pro Preview (Non-reasoning)ClosedAmazon | 23.1 | $3.4 | 120 | 1.1 s |
| 110 | ▼ 1 | OGPT-4.1 miniClosedOpenAI | 22.9 | $0.70 | 73 | 0.9 s |
| 111 | ▼ 1 | OGPT-5 (ChatGPT)ClosedOpenAI | 21.8 | $3.4 | 141 | 0.9 s |
| 112 | ▼ 1 | GGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle | 21.7 | $0.18 | — | — |
| 113 | ▼ 1 | XGrok 3 Reasoning BetaClosedxAI | 21.6 | — | — | — |
| 114 | ▼ 1 | MMistral Medium 3.1ClosedMistral | 21.3 | $0.80 | 83 | 1.4 s |
| 115 | ▼ 1 | OGPT-5 mini (minimal)ClosedOpenAI | 20.7 | $0.69 | 76 | 1.2 s |
| 116 | ▼ 1 | GGemini 2.5 Flash (Non-reasoning)ClosedGoogle | 20.6 | $0.85 | 176 | 0.6 s |
| 117 | ▼ 1 | Oo1-miniClosedOpenAI | 20.4 | — | — | — |
| 118 | ▼ 1 | OGPT-4.5 (Preview)ClosedOpenAI | 20.0 | — | — | — |
| 119 | ▼ 1 | GGemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle | 19.6 | — | — | — |
| 120 | ▼ 1 | GGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle | 19.4 | $0.18 | — | — |
| 121 | ▼ 1 | MMotif-2-12.7B-ReasoningClosedMotif Technologies | 19.1 | — | — | — |
| 122 | ▼ 1 | ANova PremierClosedAmazon | 19.0 | $5.0 | 31 | 3.1 s |
| 123 | ▼ 1 | USolar Pro 2 (Preview) (Reasoning)ClosedUpstage | 18.8 | — | — | — |
| 124 | ▼ 1 | MMagistral Medium 1ClosedMistral | 18.8 | — | — | — |
| 125 | ▼ 1 | MMistral Medium 3ClosedMistral | 18.8 | $0.80 | 60 | 1.3 s |
| 126 | ▼ 1 | AClaude 3.5 HaikuClosedAnthropic | 18.7 | $1.6 | — | — |
| 126 | ▼ 1 | MDevstral MediumClosedMistral | 18.7 | $0.80 | 127 | 1.2 s |
| 128 | ▼ 1 | OGPT-4o (Aug '24)ClosedOpenAI | 18.6 | $4.4 | 86 | 1.1 s |
| 129 | ▼ 1 | OGPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI | 18.6 | — | — | — |
| 130 | ▼ 1 | GGemini 2.0 Flash (Feb '25)ClosedGoogle | 18.5 | $0.26 | — | — |
| 131 | ▼ 1 | GGemini 2.0 Pro Experimental (Feb '25)ClosedGoogle | 18.1 | — | — | — |
| 132 | ▼ 1 | ANova 2.0 Lite (Non-reasoning)ClosedAmazon | 18.0 | $0.85 | 153 | 1.2 s |
| 133 | ▼ 1 | AClaude 3 OpusClosedAnthropic | 18.0 | $30 | — | — |
| 134 | ▼ 1 | PSonar ReasoningClosedPerplexity | 17.9 | — | — | — |
| 135 | ▼ 1 | GGemini 2.5 Flash Preview (Non-reasoning)ClosedGoogle | 17.8 | — | — | — |
| 136 | ▼ 1 | GGemini 2.5 Flash-Lite (Reasoning)ClosedGoogle | 17.6 | $0.18 | 276 | 26 s |
| 137 | ▼ 1 | OGPT-4o (Nov '24)ClosedOpenAI | 17.3 | $4.4 | 108 | 1.1 s |
| 138 | ▼ 1 | GGemini 2.0 Flash (experimental)ClosedGoogle | 16.8 | $0.000 | — | — |
| 139 | ▼ 1 | ANova 2.0 Omni (Non-reasoning)ClosedAmazon | 16.6 | $0.85 | 173 | 1.4 s |
| 140 | ▼ 1 | AQwen2.5 MaxClosedAlibaba | 16.3 | $2.8 | 45 | 3.3 s |
| 141 | ▼ 1 | GGemini 1.5 Pro (Sep '24)ClosedGoogle | 16.0 | — | — | — |
| 141 | ▼ 1 | USolar Pro 2 (Preview) (Non-reasoning)ClosedUpstage | 16.0 | — | — | — |
| 143 | ▼ 1 | AClaude 3.5 Sonnet (Oct '24)ClosedAnthropic | 15.9 | $6.0 | — | — |
| 144 | ▼ 1 | PSonarClosedPerplexity | 15.5 | — | — | — |
| 145 | ▼ 1 | PSonar ProClosedPerplexity | 15.2 | — | — | — |
| 146 | ▼ 1 | USolar Pro 2 (Reasoning)ClosedUpstage | 14.9 | — | — | — |
| 147 | ▼ 1 | GGemini 2.0 Flash-Lite (Feb '25)ClosedGoogle | 14.7 | — | — | — |
| 148 | ▼ 1 | OGPT-4o (May '24)ClosedOpenAI | 14.5 | $7.5 | 91 | 1.4 s |
| 149 | ▼ 1 | GGemini 2.0 Flash-Lite (Preview)ClosedGoogle | 14.5 | — | — | — |
| 150 | ▼ 1 | AClaude 3.5 Sonnet (June '24)ClosedAnthropic | 14.2 | $6.0 | — | — |
| 151 | ▼ 1 | OGPT-4o (ChatGPT)ClosedOpenAI | 14.1 | — | — | — |
| 152 | ▼ 1 | OGPT-5 nano (minimal)ClosedOpenAI | 13.8 | $0.14 | 137 | 1.0 s |
| 153 | ▼ 1 | GGemini 1.5 Flash (Sep '24)ClosedGoogle | 13.8 | — | — | — |
| 154 | ▼ 1 | OGPT-4 TurboClosedOpenAI | 13.7 | $15 | 26 | 2.8 s |
| 155 | ▼ 1 | USolar Pro 2 (Non-reasoning)ClosedUpstage | 13.6 | — | — | — |
| 156 | ▼ 1 | ANova ProClosedAmazon | 13.5 | $1.4 | — | — |
| 157 | ▼ 1 | XGrok BetaClosedxAI | 13.3 | — | — | — |
| 158 | ▼ 1 | OGPT-4.1 nanoClosedOpenAI | 13.0 | $0.18 | 172 | 0.7 s |
| 159 | ▼ 1 | OGPT-4ClosedOpenAI | 12.8 | $38 | — | — |
| 160 | ▼ 1 | GGemini 2.5 Flash-Lite (Non-reasoning)ClosedGoogle | 12.7 | $0.18 | 215 | 0.5 s |
| 161 | ▼ 1 | ANova LiteClosedAmazon | 12.7 | $0.11 | 151 | 1.1 s |
| 162 | ▼ 1 | OGPT-4o miniClosedOpenAI | 12.6 | $0.26 | 33 | 3.6 s |
| 163 | ▼ 1 | GGemini 2.0 Flash Thinking Experimental (Dec '24)ClosedGoogle | 12.3 | — | — | — |
| 164 | ▼ 1 | AClaude 3 HaikuClosedAnthropic | 12.3 | $0.50 | 134 | 1.2 s |
| 165 | ▼ 1 | MMistral SabaClosedMistral | 12.1 | — | — | — |
| 166 | ▼ 1 | GGemini 1.5 Pro (May '24)ClosedGoogle | 12.0 | — | — | — |
| 167 | ▼ 1 | AQwen2.5 TurboClosedAlibaba | 12.0 | $0.088 | 63 | 2.4 s |
| 168 | ▼ 1 | RReka Flash (Sep '24)ClosedReka AI | 12.0 | $0.35 | 58 | 2.0 s |
| 169 | ▼ 1 | GGemini 1.5 Flash-8BClosedGoogle | 11.1 | — | — | — |
| 170 | ▼ 1 | GGemini 1.5 Flash (May '24)ClosedGoogle | 10.5 | — | — | — |
| 171 | ▼ 1 | AClaude 3 SonnetClosedAnthropic | 10.3 | $6.0 | — | — |
| 172 | ▼ 1 | ANova MicroClosedAmazon | 10.3 | $0.061 | 275 | 0.9 s |
| 173 | ▼ 1 | GGemini 1.0 UltraClosedGoogle | 10.1 | — | — | — |
| 174 | ▼ 1 | MMistral Large (Feb '24)ClosedMistral | 9.9 | $6.0 | — | — |
| 175 | ▼ 1 | AClaude 2.1ClosedAnthropic | 9.3 | — | — | — |
| 176 | ▼ 1 | AClaude 2.0ClosedAnthropic | 9.1 | — | — | — |
| 177 | ▼ 1 | MMistral Small (Feb '24)ClosedMistral | 9.0 | $1.5 | 138 | 0.7 s |
| 178 | ▼ 1 | MMistral MediumClosedMistral | 9.0 | $4.1 | 74 | 1.3 s |
| 179 | ▼ 1 | OGPT-3.5 TurboClosedOpenAI | 9.0 | $0.75 | — | — |
| 180 | ▼ 1 | LLFM 40BClosedLiquid AI | 8.8 | — | — | — |
| 181 | ▼ 1 | GPALM-2ClosedGoogle | 8.6 | — | — | — |
| 182 | ▼ 1 | GGemini 1.0 ProClosedGoogle | 8.5 | — | — | — |
| 183 | ▼ 1 | AClaude InstantClosedAnthropic | 7.4 | — | — | — |
