| 1 | — | OGPT-5.5 (xhigh)閉源OpenAI | 60.2 | $11 | 63 | 73 秒 |
| 2 | — | OGPT-5.5 (high)閉源OpenAI | 58.9 | $11 | 62 | 24 秒 |
| 3 | — | AClaude Opus 4.7 (Adaptive Reasoning, Max Effort)閉源Anthropic | 57.3 | $11 | 43 | 22 秒 |
| 4 | — | GGemini 3.1 Pro Preview閉源Google | 57.2 | $4.5 | 112 | 29 秒 |
| 5 | — | OGPT-5.4 (xhigh)閉源OpenAI | 56.8 | $5.6 | 80 | 228 秒 |
| 6 | — | OGPT-5.5 (medium)閉源OpenAI | 56.7 | $11 | 58 | 8.2 秒 |
| 7 | — | OGPT-5.3 Codex (xhigh)閉源OpenAI | 53.6 | $4.8 | 74 | 96 秒 |
| 8 | — | XGrok 4.3閉源xAI | 53.2 | $1.6 | 72 | 15 秒 |
| 9 | — | AClaude Opus 4.6 (Adaptive Reasoning, Max Effort)閉源Anthropic | 53.0 | $11 | 40 | 12 秒 |
| 10 | — | MMuse Spark閉源Meta | 52.2 | — | — | — |
| 11 | — | AClaude Opus 4.7 (Non-reasoning, High Effort)閉源Anthropic | 51.8 | $11 | 37 | 1.7 秒 |
| 12 | — | AQwen3.6 Max Preview閉源Alibaba | 51.8 | $2.9 | 36 | 3.5 秒 |
| 13 | — | AClaude Sonnet 4.6 (Adaptive Reasoning, Max Effort)閉源Anthropic | 51.7 | $6.6 | 51 | 111 秒 |
| 14 | — | OGPT-5.2 (xhigh)閉源OpenAI | 51.3 | $4.8 | 63 | 156 秒 |
| 15 | — | OGPT-5.5 (low)閉源OpenAI | 50.8 | $11 | 58 | 2.0 秒 |
| 16 | — | AQwen3.6 Plus閉源Alibaba | 50.0 | $1.1 | 53 | 3.1 秒 |
| 17 | — | AClaude Opus 4.5 (Reasoning)閉源Anthropic | 49.7 | $11 | 45 | 9.8 秒 |
| 18 | — | XGrok 4.20 0309 v2 (Reasoning)閉源xAI | 49.3 | $3.0 | 87 | 25 秒 |
| 19 | — | XMiMo-V2-Pro閉源Xiaomi | 49.2 | $1.5 | 62 | 3.2 秒 |
| 20 | — | OGPT-5.2 Codex (xhigh)閉源OpenAI | 49.0 | $4.8 | 99 | 107 秒 |
| 21 | — | OGPT-5.4 mini (xhigh)閉源OpenAI | 48.9 | $1.7 | 155 | 7.9 秒 |
| 22 | — | XGrok 4.20 0309 (Reasoning)閉源xAI | 48.5 | $3.0 | 85 | 28 秒 |
| 23 | — | GGemini 3 Pro Preview (high)閉源Google | 48.4 | $4.5 | 126 | 47 秒 |
| 24 | — | OGPT-5.4 (low)閉源OpenAI | 47.9 | $5.6 | 67 | 2.0 秒 |
| 25 | — | OGPT-5.1 (high)閉源OpenAI | 47.7 | $3.4 | 136 | 25 秒 |
| 26 | — | ZGLM-5-Turbo閉源Z AI | 46.8 | — | — | — |
| 27 | — | OGPT-5.2 (medium)閉源OpenAI | 46.6 | $4.8 | — | — |
| 28 | — | AClaude Opus 4.6 (Non-reasoning, High Effort)閉源Anthropic | 46.5 | $11 | 37 | 1.7 秒 |
| 29 | — | GGemini 3 Flash Preview (Reasoning)閉源Google | 46.4 | $1.1 | 162 | 6.8 秒 |
| 30 | — | XMiMo-V2-Omni-0327閉源Xiaomi | 44.9 | $0.80 | 107 | 2.2 秒 |
| 31 | — | OGPT-5 (high)閉源OpenAI | 44.6 | $3.4 | 71 | 88 秒 |
| 31 | — | OGPT-5 Codex (high)閉源OpenAI | 44.6 | $3.4 | 161 | 9.7 秒 |
| 33 | — | AClaude Sonnet 4.6 (Non-reasoning, High Effort)閉源Anthropic | 44.4 | $6.6 | 43 | 1.4 秒 |
| 34 | — | OGPT-5.4 nano (xhigh)閉源OpenAI | 44.0 | $0.46 | 152 | 4.8 秒 |
| 35 | — | XMiMo-V2-Omni閉源Xiaomi | 43.4 | $0.000 | 110 | 2.1 秒 |
| 36 | — | OGPT-5.1 Codex (high)閉源OpenAI | 43.1 | $3.4 | 167 | 5.6 秒 |
| 37 | — | AClaude Opus 4.5 (Non-reasoning)閉源Anthropic | 43.1 | $11 | 44 | 1.6 秒 |
| 38 | — | AClaude 4.5 Sonnet (Reasoning)閉源Anthropic | 43.0 | $6.6 | 40 | 9.1 秒 |
| 39 | — | ZGLM 5V Turbo (Reasoning)閉源Z AI | 42.9 | — | — | — |
| 40 | — | AClaude Sonnet 4.6 (Non-reasoning, Low Effort)閉源Anthropic | 42.6 | $6.6 | 43 | 1.2 秒 |
| 41 | — | OGPT-5 (medium)閉源OpenAI | 42.0 | $3.4 | 82 | 41 秒 |
| 42 | — | AClaude 4.1 Opus (Reasoning)閉源Anthropic | 42.0 | $33 | 28 | 12 秒 |
| 43 | — | XGrok 4閉源xAI | 41.5 | $8.5 | 42 | 20 秒 |
| 44 | — | GGemini 3 Pro Preview (low)閉源Google | 41.3 | $4.5 | — | — |
| 45 | — | OGPT-5 mini (high)閉源OpenAI | 41.2 | $0.69 | 72 | 106 秒 |
| 46 | — | OGPT-5.5 (Non-reasoning)閉源OpenAI | 40.9 | $11 | 56 | 1.0 秒 |
| 47 | — | Oo3-pro閉源OpenAI | 40.7 | $35 | 29 | 92 秒 |
| 48 | — | AQwen3 Max Thinking閉源Alibaba | 39.9 | $2.4 | 38 | 3.7 秒 |
| 49 | — | OGPT-5 (low)閉源OpenAI | 39.2 | $3.4 | 75 | 8.5 秒 |
| 50 | — | AClaude 4 Opus (Reasoning)閉源Anthropic | 39.0 | $33 | 30 | 7.6 秒 |
| 51 | — | OGPT-5 mini (medium)閉源OpenAI | 38.9 | $0.69 | 73 | 17 秒 |
| 52 | — | AClaude 4 Sonnet (Reasoning)閉源Anthropic | 38.7 | $6.6 | 40 | 10 秒 |
| 53 | — | OGPT-5.1 Codex mini (high)閉源OpenAI | 38.6 | $0.69 | 197 | 3.6 秒 |
| 53 | — | AQwen3.5 Omni Plus閉源Alibaba | 38.6 | $1.5 | 54 | 2.4 秒 |
| 55 | — | XGrok 4.1 Fast (Reasoning)閉源xAI | 38.6 | $0.28 | 78 | 13 秒 |
| 56 | — | SStep 3.5 Flash 2603閉源StepFun | 38.5 | $0.000 | 175 | 1.0 秒 |
| 57 | — | Oo3閉源OpenAI | 38.4 | $3.5 | 82 | 8.3 秒 |
| 58 | — | OGPT-5.4 nano (medium)閉源OpenAI | 38.1 | $0.46 | 153 | 3.1 秒 |
| 59 | — | OGPT-5.4 mini (medium)閉源OpenAI | 37.7 | $1.7 | 159 | 11 秒 |
| 60 | — | AClaude 4.5 Sonnet (Non-reasoning)閉源Anthropic | 37.1 | $6.6 | 38 | 1.6 秒 |
| 61 | — | AClaude 4.5 Haiku (Reasoning)閉源Anthropic | 37.1 | $2.2 | 95 | 13 秒 |
| 62 | — | AClaude 4.1 Opus (Non-reasoning)閉源Anthropic | 36.0 | $33 | 29 | 2.0 秒 |
| 63 | — | ANova 2.0 Pro Preview (medium)閉源Amazon | 35.7 | $3.4 | 143 | 13 秒 |
| 64 | — | OGPT-5.4 (Non-reasoning)閉源OpenAI | 35.4 | $5.6 | 59 | 0.8 秒 |
| 65 | — | XGrok 4 Fast (Reasoning)閉源xAI | 35.1 | $0.28 | 54 | 9.3 秒 |
| 66 | — | GGemini 3 Flash Preview (Non-reasoning)閉源Google | 35.1 | $1.1 | 173 | 1.1 秒 |
| 67 | — | AClaude 3.7 Sonnet (Reasoning)閉源Anthropic | 34.7 | — | — | — |
| 68 | — | GGemini 2.5 Pro閉源Google | 34.6 | $3.4 | 127 | 26 秒 |
| 69 | — | ANova 2.0 Lite (high)閉源Amazon | 34.5 | $0.85 | 150 | 13 秒 |
| 70 | — | OGPT-5.2 (Non-reasoning)閉源OpenAI | 33.6 | $4.8 | 60 | 0.9 秒 |
| 71 | — | BDoubao Seed Code閉源ByteDance Seed | 33.5 | — | — | — |
| 71 | — | GGemini 3.1 Flash-Lite Preview閉源Google | 33.5 | $0.56 | 326 | 5.7 秒 |
| 73 | — | Oo4-mini (high)閉源OpenAI | 33.1 | $1.9 | 123 | 26 秒 |
| 74 | — | AClaude 4 Opus (Non-reasoning)閉源Anthropic | 33.0 | $33 | 30 | 1.9 秒 |
| 74 | — | AClaude 4 Sonnet (Non-reasoning)閉源Anthropic | 33.0 | $6.6 | 39 | 1.3 秒 |
| 76 | — | IMercury 2閉源Inception | 32.8 | $0.38 | 685 | 3.3 秒 |
| 77 | — | AQwen3 Max Thinking (Preview)閉源Alibaba | 32.5 | $2.4 | 40 | 4.1 秒 |
| 78 | — | XGrok 3 mini Reasoning (high)閉源xAI | 32.1 | $0.35 | 169 | 0.7 秒 |
| 79 | — | ANova 2.0 Pro Preview (low)閉源Amazon | 31.9 | $3.4 | 140 | 7.4 秒 |
| 80 | — | AQwen3 Max閉源Alibaba | 31.4 | $3.0 | 32 | 2.8 秒 |
| 81 | — | GGemini 2.5 Flash Preview (Sep '25) (Reasoning)閉源Google | 31.1 | — | — | — |
| 82 | — | AClaude 4.5 Haiku (Non-reasoning)閉源Anthropic | 31.1 | $2.2 | 86 | 0.7 秒 |
| 83 | — | AClaude 3.7 Sonnet (Non-reasoning)閉源Anthropic | 30.8 | $6.6 | — | — |
| 84 | — | Oo1閉源OpenAI | 30.8 | $26 | 93 | 36 秒 |
| 85 | — | GGemini 2.5 Pro Preview (Mar' 25)閉源Google | 30.3 | — | — | — |
| 86 | — | ANova 2.0 Lite (medium)閉源Amazon | 29.7 | $0.85 | 171 | 17 秒 |
| 87 | — | XGrok 4.20 0309 (Non-reasoning)閉源xAI | 29.7 | $3.0 | 87 | 0.7 秒 |
| 88 | — | GGemini 2.5 Pro Preview (May' 25)閉源Google | 29.5 | $3.4 | — | — |
| 89 | — | BERNIE 5.0 Thinking Preview閉源Baidu | 29.1 | — | — | — |
| 90 | — | XGrok 4.20 0309 v2 (Non-reasoning)閉源xAI | 29.0 | $3.0 | 84 | 0.7 秒 |
| 91 | — | XGrok Code Fast 1閉源xAI | 28.7 | $0.53 | 70 | 6.4 秒 |
| 92 | — | ANova 2.0 Omni (medium)閉源Amazon | 28.0 | $0.85 | — | — |
| 93 | — | OGPT-5.1 (Non-reasoning)閉源OpenAI | 27.4 | $3.4 | 126 | 1.0 秒 |
| 94 | — | MMagistral Medium 1.2閉源Mistral | 27.1 | $2.8 | 40 | 1.6 秒 |
| 95 | — | GGemini 2.5 Flash (Reasoning)閉源Google | 27.0 | $0.85 | 219 | 14 秒 |
| 96 | — | OGPT-5 nano (high)閉源OpenAI | 26.8 | $0.14 | 127 | 101 秒 |
| 97 | — | OGPT-4.1閉源OpenAI | 26.3 | $3.5 | 105 | 1.0 秒 |
| 98 | — | AQwen3 Max (Preview)閉源Alibaba | 26.1 | $2.4 | 51 | 4.2 秒 |
| 99 | — | OGPT-5 nano (medium)閉源OpenAI | 25.9 | $0.14 | 142 | 42 秒 |
| 100 | — | AQwen3.5 Omni Flash閉源Alibaba | 25.9 | $0.28 | 241 | 1.9 秒 |
| 100 | — | USolar Pro 3閉源Upstage | 25.9 | — | — | — |
| 102 | — | Oo3-mini閉源OpenAI | 25.9 | $1.9 | 129 | 8.8 秒 |
| 103 | — | Oo1-pro閉源OpenAI | 25.8 | $263 | — | — |
| 104 | — | GGemini 2.5 Flash Preview (Sep '25) (Non-reasoning)閉源Google | 25.7 | — | — | — |
| 105 | — | CJT-MINI閉源China Mobile | 25.4 | — | — | — |
| 106 | — | Oo3-mini (high)閉源OpenAI | 25.2 | $1.9 | 133 | 32 秒 |
| 107 | — | XGrok 3閉源xAI | 25.2 | $6.0 | 34 | 1.8 秒 |
| 108 | — | PSonar Reasoning Pro閉源Perplexity | 24.6 | — | — | — |
| 109 | — | ANova 2.0 Lite (low)閉源Amazon | 24.6 | $0.85 | 156 | 8.3 秒 |
| 110 | — | OGPT-5.4 nano (Non-Reasoning)閉源OpenAI | 24.4 | $0.46 | 146 | 0.6 秒 |
| 111 | — | GGemini 2.5 Flash Preview (Reasoning)閉源Google | 24.3 | — | — | — |
| 112 | — | OGPT-5 (minimal)閉源OpenAI | 23.9 | $3.4 | 71 | 1.7 秒 |
| 113 | — | Oo1-preview閉源OpenAI | 23.7 | $29 | — | — |
| 114 | — | XGrok 4.1 Fast (Non-reasoning)閉源xAI | 23.6 | $0.28 | 65 | 0.7 秒 |
| 115 | — | OGPT-5.4 mini (Non-Reasoning)閉源OpenAI | 23.3 | $1.7 | 148 | 0.6 秒 |
| 116 | — | ANova 2.0 Omni (low)閉源Amazon | 23.2 | $0.85 | — | — |
| 117 | — | XGrok 4 Fast (Non-reasoning)閉源xAI | 23.1 | $0.28 | 44 | 0.7 秒 |
| 118 | — | KMi:dm K 2.5 Pro閉源Korea Telecom | 23.1 | — | — | — |
| 118 | — | ANova 2.0 Pro Preview (Non-reasoning)閉源Amazon | 23.1 | $3.4 | 107 | 1.1 秒 |
| 120 | — | OGPT-4.1 mini閉源OpenAI | 22.9 | $0.70 | 73 | 0.8 秒 |
| 121 | — | OGPT-5 (ChatGPT)閉源OpenAI | 21.8 | $3.4 | 163 | 0.8 秒 |
| 122 | — | GGemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)閉源Google | 21.7 | $0.18 | — | — |
| 123 | — | XGrok 3 Reasoning Beta閉源xAI | 21.6 | — | — | — |
| 124 | — | MMistral Medium 3.1閉源Mistral | 21.3 | $0.80 | 88 | 1.5 秒 |
| 125 | — | OGPT-5 mini (minimal)閉源OpenAI | 20.7 | $0.69 | 72 | 1.3 秒 |
| 126 | — | GGemini 2.5 Flash (Non-reasoning)閉源Google | 20.6 | $0.85 | 191 | 0.7 秒 |
| 127 | — | Oo1-mini閉源OpenAI | 20.4 | — | — | — |
| 128 | — | OGPT-4.5 (Preview)閉源OpenAI | 20.0 | — | — | — |
| 129 | — | GGemini 2.0 Flash Thinking Experimental (Jan '25)閉源Google | 19.6 | — | — | — |
| 130 | — | GGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)閉源Google | 19.4 | $0.18 | — | — |
| 131 | — | MMotif-2-12.7B-Reasoning閉源Motif Technologies | 19.1 | — | — | — |
| 132 | — | ANova Premier閉源Amazon | 19.0 | $5.0 | 28 | 3.1 秒 |
| 133 | — | USolar Pro 2 (Preview) (Reasoning)閉源Upstage | 18.8 | — | — | — |
| 134 | — | MMagistral Medium 1閉源Mistral | 18.8 | — | — | — |
| 135 | — | MMistral Medium 3閉源Mistral | 18.8 | $0.80 | 45 | 1.5 秒 |
| 136 | — | AClaude 3.5 Haiku閉源Anthropic | 18.7 | $1.8 | — | — |
| 136 | — | MDevstral Medium閉源Mistral | 18.7 | $0.80 | 78 | 1.4 秒 |
| 138 | — | OGPT-4o (Aug '24)閉源OpenAI | 18.6 | $4.4 | 91 | 1.4 秒 |
| 139 | — | OGPT-4o (March 2025, chatgpt-4o-latest)閉源OpenAI | 18.6 | — | — | — |
| 140 | — | GGemini 2.0 Flash (Feb '25)閉源Google | 18.5 | $0.26 | — | — |
| 141 | — | GGemini 2.0 Pro Experimental (Feb '25)閉源Google | 18.1 | — | — | — |
| 142 | — | ANova 2.0 Lite (Non-reasoning)閉源Amazon | 18.0 | $0.85 | 134 | 1.3 秒 |
| 143 | — | AClaude 3 Opus閉源Anthropic | 18.0 | $33 | — | — |
| 144 | — | PSonar Reasoning閉源Perplexity | 17.9 | — | — | — |
| 145 | — | GGemini 2.5 Flash Preview (Non-reasoning)閉源Google | 17.8 | — | — | — |
| 146 | — | GGemini 2.5 Flash-Lite (Reasoning)閉源Google | 17.6 | $0.18 | 235 | 28 秒 |
| 147 | — | OGPT-4o (Nov '24)閉源OpenAI | 17.3 | $4.4 | 112 | 0.9 秒 |
| 148 | — | GGemini 2.0 Flash (experimental)閉源Google | 16.8 | $0.000 | — | — |
| 149 | — | ANova 2.0 Omni (Non-reasoning)閉源Amazon | 16.6 | $0.85 | 201 | 1.4 秒 |
| 150 | — | AQwen2.5 Max閉源Alibaba | 16.3 | $2.8 | 46 | 3.3 秒 |
| 151 | — | GGemini 1.5 Pro (Sep '24)閉源Google | 16.0 | — | — | — |
| 151 | — | USolar Pro 2 (Preview) (Non-reasoning)閉源Upstage | 16.0 | — | — | — |
| 153 | — | AClaude 3.5 Sonnet (Oct '24)閉源Anthropic | 15.9 | $6.6 | — | — |
| 154 | — | PSonar閉源Perplexity | 15.5 | — | — | — |
| 155 | — | PSonar Pro閉源Perplexity | 15.2 | — | — | — |
| 156 | — | USolar Pro 2 (Reasoning)閉源Upstage | 14.9 | — | — | — |
| 157 | — | GGemini 2.0 Flash-Lite (Feb '25)閉源Google | 14.7 | — | — | — |
| 158 | — | OGPT-4o (May '24)閉源OpenAI | 14.5 | $7.5 | 82 | 1.2 秒 |
| 159 | — | GGemini 2.0 Flash-Lite (Preview)閉源Google | 14.5 | — | — | — |
| 160 | — | AClaude 3.5 Sonnet (June '24)閉源Anthropic | 14.2 | $6.6 | — | — |
| 161 | — | OGPT-4o (ChatGPT)閉源OpenAI | 14.1 | — | — | — |
| 162 | — | OGPT-5 nano (minimal)閉源OpenAI | 13.8 | $0.14 | 121 | 1.0 秒 |
| 163 | — | GGemini 1.5 Flash (Sep '24)閉源Google | 13.8 | — | — | — |
| 164 | — | OGPT-4 Turbo閉源OpenAI | 13.7 | $15 | 30 | 2.9 秒 |
| 165 | — | USolar Pro 2 (Non-reasoning)閉源Upstage | 13.6 | — | — | — |
| 166 | — | ANova Pro閉源Amazon | 13.5 | $1.4 | — | — |
| 167 | — | XGrok Beta閉源xAI | 13.3 | — | — | — |
| 168 | — | OGPT-4.1 nano閉源OpenAI | 13.0 | $0.18 | 122 | 0.7 秒 |
| 169 | — | OGPT-4閉源OpenAI | 12.8 | $38 | — | — |
| 170 | — | GGemini 2.5 Flash-Lite (Non-reasoning)閉源Google | 12.7 | $0.18 | 233 | 1.1 秒 |
| 171 | — | ANova Lite閉源Amazon | 12.7 | $0.11 | 164 | 1.0 秒 |
| 172 | — | OGPT-4o mini閉源OpenAI | 12.6 | $0.26 | 50 | 2.7 秒 |
| 173 | — | GGemini 2.0 Flash Thinking Experimental (Dec '24)閉源Google | 12.3 | — | — | — |
| 174 | — | AClaude 3 Haiku閉源Anthropic | 12.3 | $0.50 | — | — |
| 175 | — | MMistral Saba閉源Mistral | 12.1 | — | — | — |
| 176 | — | GGemini 1.5 Pro (May '24)閉源Google | 12.0 | — | — | — |
| 177 | — | AQwen2.5 Turbo閉源Alibaba | 12.0 | $0.088 | 64 | 2.4 秒 |
| 178 | — | RReka Flash (Sep '24)閉源Reka AI | 12.0 | $0.35 | 58 | 2.3 秒 |
| 179 | — | GGemini 1.5 Flash-8B閉源Google | 11.1 | — | — | — |
| 180 | — | GGemini 1.5 Flash (May '24)閉源Google | 10.5 | — | — | — |
| 181 | — | AClaude 3 Sonnet閉源Anthropic | 10.3 | $6.0 | — | — |
| 182 | — | ANova Micro閉源Amazon | 10.3 | $0.061 | 279 | 0.9 秒 |
| 183 | — | GGemini 1.0 Ultra閉源Google | 10.1 | — | — | — |
| 184 | — | MMistral Large (Feb '24)閉源Mistral | 9.9 | $6.0 | — | — |
| 185 | — | AClaude 2.1閉源Anthropic | 9.3 | — | — | — |
| 186 | — | AClaude 2.0閉源Anthropic | 9.1 | — | — | — |
| 187 | — | MMistral Small (Feb '24)閉源Mistral | 9.0 | $1.5 | 128 | 0.8 秒 |
| 188 | — | MMistral Medium閉源Mistral | 9.0 | $4.1 | 86 | 1.5 秒 |
| 189 | — | OGPT-3.5 Turbo閉源OpenAI | 9.0 | $0.75 | — | — |
| 190 | — | LLFM 40B閉源Liquid AI | 8.8 | — | — | — |
| 191 | — | GPALM-2閉源Google | 8.6 | — | — | — |
| 192 | — | GGemini 1.0 Pro閉源Google | 8.5 | — | — | — |
| 193 | — | AClaude Instant閉源Anthropic | 7.4 | — | — | — |
