| 1 | Gemini 3.7 Flash (Reasoning, Medium) | 99.8% | $0.013 | 9.9s | 98% |
| 2 | Qwen 3.7 Flash (Reasoning) | 98.3% | $0.0009 | 33.3s | 92% |
| 3 | Gemini 2.5 Flash Lite (Reasoning) | 96.8% | $0.0020 | 17.6s | 90% |
| 4 | Gemini 3.8 Flash (Reasoning, Medium) | 100.0% | $0.020 | 13.0s | 100% |
| 5 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 96.2% | $0.0004 | 16.9s | 88% |
| 6 | Gemma 4 31B | 97.4% | $0.0009 | 37.9s | 93% |
| 7 | Z.AI GLM 5 Turbo | 97.4% | $0.0072 | 17.1s | 91% |
| 8 | Inception Mercury 2 | 95.0% | $0.0030 | 4.6s | 87% |
| 9 | GPT-5.6 Terra | 96.6% | $0.011 | 3.8s | 91% |
| 10 | Gemini 2.5 Flash (Reasoning) | 96.9% | $0.0079 | 12.5s | 89% |
| 11 | ByteDance Seed 1.6 Flash | 94.1% | $0.0009 | 12.0s | 85% |
| 12 | GPT-5.4 Mini (Reasoning, Low) | 95.2% | $0.0055 | 6.7s | 85% |
| 13 | MiniMax M2.7 | 95.5% | $0.0022 | 29.4s | 88% |
| 14 | DeepSeek V4.1 Flash (Reasoning, High) | 97.3% | $0.0046 | 30.8s | 88% |
| 15 | Gemini 3 Flash (Preview, Reasoning) | 96.7% | $0.011 | 18.0s | 91% |
| 16 | DeepSeek V4 Flash (Reasoning) | 95.9% | $0.0010 | 40.3s | 89% |
| 17 | Gemini 3 Flash (Preview) | 93.9% | $0.0031 | 4.5s | 83% |
| 18 | Muse Spark 1.1 (Reasoning, Minimal) | 96.5% | $0.011 | 10.5s | 88% |
| 19 | Gemini 3.6 Flash (Reasoning, Minimal) | 94.6% | $0.011 | 3.3s | 87% |
| 20 | Gemini 3.5 Flash (Reasoning, Minimal) | 94.8% | $0.011 | 3.6s | 87% |
| 21 | Grok 4.5 (Reasoning, Low) | 98.0% | $0.013 | 29.6s | 92% |
| 22 | GPT-5.4 | 95.7% | $0.013 | 8.8s | 88% |
| 23 | Z.AI GLM 5.2 (Reasoning, High) | 97.3% | $0.0100 | 27.9s | 89% |
| 24 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 93.5% | $0.0030 | 2.1s | 79% |
| 25 | Muse Spark 1.1 (Reasoning, Medium) | 96.9% | $0.016 | 16.1s | 89% |
| 26 | MiniMax M2.5 | 93.5% | $0.0020 | 25.5s | 84% |
| 27 | ByteDance Seed 2.0 Lite | 98.1% | $0.0067 | 1.1m | 93% |
| 28 | GPT-5.6 Sol | 97.6% | $0.026 | 6.4s | 92% |
| 29 | Muse Glimmer 30B (Reasoning, Medium) | 96.1% | $0.0036 | 49.9s | 87% |
| 30 | GPT-5.6 Luna (Reasoning) | 94.1% | $0.010 | 9.3s | 83% |
| 31 | Grok 4.20 (Reasoning) | 98.5% | $0.015 | 45.4s | 92% |
| 32 | Gemini 2.5 Flash | 91.4% | $0.0025 | 2.8s | 77% |
| 33 | Qwen 3.5 Flash | 97.1% | $0.0038 | 1.0m | 88% |
| 34 | Xiaomi MIMO v2.5 Pro | 95.4% | $0.0091 | 37.0s | 87% |
| 35 | o4 Mini | 97.4% | $0.019 | 28.1s | 90% |
| 36 | ByteDance Seed 1.6 | 96.8% | $0.0067 | 1.0m | 91% |
| 37 | Xiaomi MIMO v2.5 | 94.7% | $0.0058 | 21.8s | 80% |
| 38 | Mistral Small 4 (Reasoning) | 92.2% | $0.0020 | 16.3s | 78% |
| 39 | GPT-5.6 Terra (Reasoning) | 95.3% | $0.021 | 10.3s | 88% |
| 40 | Claude Opus 4.5 | 99.8% | $0.041 | 9.7s | 98% |
| 41 | Claude Sonnet 4.5 | 96.3% | $0.024 | 8.9s | 88% |
| 42 | Kimi K3 (Reasoning, Low) | 98.3% | $0.024 | 36.5s | 93% |
| 43 | Claude Sonnet 4 | 95.6% | $0.023 | 9.0s | 88% |
| 44 | Z.AI GLM 5 | 97.9% | $0.013 | 56.4s | 90% |
| 45 | Muse Spark 1.3 (Reasoning, Medium) | 98.6% | $0.022 | 43.0s | 93% |
| 46 | Muse Spark 1.2 (Reasoning, Medium) | 96.0% | $0.021 | 16.6s | 87% |
| 47 | MiniMax M3 | 96.9% | $0.0046 | 1.4m | 90% |
| 48 | Z.AI GLM 4.7 | 96.2% | $0.0091 | 1.0m | 89% |
| 49 | Gemini 3.6 Flash (Reasoning) | 99.7% | $0.039 | 16.1s | 96% |
| 50 | GPT-5.4 (Reasoning, Low) | 94.9% | $0.020 | 13.5s | 84% |
| 51 | Gemini 3.1 Flash Lite (Preview) | 89.2% | $0.0019 | 2.2s | 73% |
| 52 | Z.AI GLM 4.7 Flash | 94.0% | $0.0018 | 1.1m | 86% |
| 53 | Qwen 3.6 35B | 96.9% | $0.013 | 51.0s | 88% |
| 54 | GPT-5.4 Mini (Reasoning) | 96.0% | $0.020 | 28.6s | 87% |
| 55 | Qwen 3.5 35B | 97.5% | $0.017 | 54.8s | 91% |
| 56 | GPT-5.5 | 96.2% | $0.030 | 7.7s | 89% |
| 57 | GPT-5 Mini | 94.8% | $0.0092 | 51.7s | 86% |
| 58 | GPT-5.2 | 95.7% | $0.024 | 24.2s | 89% |
| 59 | Qwen 3.6 Flash | 96.7% | $0.011 | 29.9s | 77% |
| 60 | Gemini 2.5 Pro | 98.4% | $0.035 | 23.2s | 93% |
| 61 | Claude Opus 4.6 | 98.5% | $0.040 | 10.2s | 94% |
| 62 | Mistral Large 3 | 87.5% | $0.0030 | 10.2s | 74% |
| 63 | Gemini 3.1 Flash Lite | 87.8% | $0.0018 | 3.2s | 71% |
| 64 | Qwen 3.5 Plus (2026-04-20) | 98.5% | $0.015 | 1.4m | 93% |
| 65 | Grok 4.5 (Reasoning, High) | 97.4% | $0.027 | 46.7s | 92% |
| 66 | DeepSeek V3 (2024-12-26) | 89.6% | $0.0019 | 15.6s | 70% |
| 67 | DeepSeek V4 Flash | 87.3% | $0.0003 | 9.3s | 68% |
| 68 | Gemini 3.5 Flash (Reasoning) | 98.9% | $0.045 | 18.1s | 94% |
| 69 | Grok 4.3 (Reasoning) | 98.4% | $0.019 | 1.4m | 90% |
| 70 | DeepSeek-V2 Chat | 89.5% | $0.0020 | 13.1s | 66% |
| 71 | GPT-5.5 (Reasoning, Low) | 96.3% | $0.040 | 14.2s | 90% |
| 72 | GPT-OSS 120B | 94.3% | $0.0020 | 1.5m | 83% |
| 73 | Gemini 3.5 Flash Lite (Reasoning) | 90.4% | $0.0029 | 2.0s | 61% |
| 74 | Z.AI GLM 4.5 | 88.7% | $0.0026 | 18.5s | 68% |
| 75 | Z.AI GLM 4.5 Air | 92.0% | $0.0025 | 39.8s | 70% |
| 76 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 97.7% | $0.0019 | 2.3m | 91% |
| 77 | Qwen 3 32B | 89.4% | $0.0010 | 27.8s | 67% |
| 78 | Thinking Machines Inkling Small (Reasoning, High) | 93.4% | $0.0066 | 55.7s | 75% |
| 79 | Z.AI GLM 5.1 | 97.6% | $0.017 | 1.6m | 90% |
| 80 | GPT-4.1 Mini | 84.4% | $0.0015 | 5.8s | 66% |
| 81 | Mistral Large 2 | 87.9% | $0.012 | 8.8s | 72% |
| 82 | Kimi K2.5 | 95.9% | $0.015 | 1.5m | 88% |
| 83 | Gemini 3.1 Flash Lite (Reasoning) | 87.0% | $0.0018 | 3.7s | 62% |
| 84 | Claude Sonnet 4.6 | 91.5% | $0.024 | 9.9s | 77% |
| 85 | DeepSeek V3.2 | 86.6% | $0.0013 | 17.2s | 66% |
| 86 | o4 Mini High | 97.1% | $0.033 | 51.3s | 90% |
| 87 | Mistral Medium 3.1 | 85.4% | $0.0029 | 7.7s | 64% |
| 88 | DeepSeek V4 Flash 0731 (Reasoning, High) | 95.5% | $0.0022 | 1.5m | 75% |
| 89 | GPT-5.6 Luna | 84.9% | $0.0048 | 3.9s | 64% |
| 90 | Qwen 3.5 122B | 96.2% | $0.026 | 1.2m | 88% |
| 91 | GPT-5.1 | 97.3% | $0.037 | 52.8s | 90% |
| 92 | Qwen 3.6 27B | 97.4% | $0.022 | 1.4m | 86% |
| 93 | Qwen 3.5 27B | 97.2% | $0.021 | 1.7m | 91% |
| 94 | ByteDance Seed 2.0 Mini | 98.0% | $0.0029 | 2.7m | 92% |
| 95 | Qwen 3.5 Plus (2026-02-15) | 89.3% | $0.0041 | 34.2s | 66% |
| 96 | Qwen 3.8 27B (Reasoning, XHigh) | 96.7% | $0.025 | 1.4m | 89% |
| 97 | Qwen 3 235B A22B Instruct 2507 | 83.6% | $0.0007 | 21.1s | 65% |
| 98 | Z.AI GLM 4.6 | 91.9% | $0.0049 | 1.3m | 76% |
| 99 | GPT-4.1 | 89.1% | $0.0081 | 10.0s | 61% |
| 100 | Writer: Palmyra X5 | 84.3% | $0.0062 | 12.1s | 66% |
| 101 | GPT-4o, Aug. 6th (temp=1) | 87.6% | $0.011 | 3.6s | 62% |
| 102 | Laguna XS 2.1 | 88.8% | $0.0005 | 19.0s | 56% |
| 103 | Gemma 4 31B (Reasoning) | 97.6% | $0.0017 | 2.8m | 92% |
| 104 | Gemma 4 26B (Reasoning) | 96.6% | $0.0022 | 2.0m | 77% |
| 105 | Grok 4.20 | 83.4% | $0.0053 | 6.4s | 62% |
| 106 | Aion 2.0 | 95.9% | $0.0084 | 1.3m | 68% |
| 107 | GPT-5.6 Sol (Reasoning) | 95.9% | $0.052 | 19.9s | 89% |
| 108 | Kimi K3 (Reasoning, High) | 98.9% | $0.044 | 1.3m | 95% |
| 109 | Qwen 3.7 Max | 98.3% | $0.045 | 1.1m | 92% |
| 110 | DeepSeek V4 Pro | 86.1% | $0.0031 | 25.6s | 60% |
| 111 | DeepSeek V3 (2025-03-24) | 86.8% | $0.0015 | 22.9s | 56% |
| 112 | Qwen 3.8 Flash (Reasoning) | 95.7% | $0.0060 | 2.6m | 88% |
| 113 | GPT-4o, Aug. 6th (temp=0) | 87.3% | $0.015 | 5.0s | 60% |
| 114 | Gemma 3 27B | 78.6% | $0.0005 | 13.3s | 60% |
| 115 | GPT-5.4 (Reasoning) | 94.5% | $0.042 | 43.1s | 84% |
| 116 | Claude Opus 4.7 (Reasoning) | 98.0% | $0.067 | 11.4s | 91% |
| 117 | Qwen 3.5 9B | 95.5% | $0.0020 | 2.4m | 76% |
| 118 | Claude Opus 5 | 97.0% | $0.052 | 10.1s | 77% |
| 119 | Claude Opus 4.7 | 92.9% | $0.052 | 7.6s | 80% |
| 120 | Hermes 3 405B | 82.2% | $0.0044 | 17.2s | 53% |
| 121 | Gemini 3.1 Pro (Preview) | 99.3% | $0.068 | 52.3s | 96% |
| 122 | Grok 4.6 (Reasoning, High) | 97.5% | $0.044 | 1.7m | 91% |
| 123 | Claude Opus 4.6 (Reasoning) | 99.2% | $0.076 | 32.0s | 96% |
| 124 | Arcee AI: Trinity Mini | 80.9% | $0.0004 | 10.3s | 47% |
| 125 | Claude Haiku 4.5 | 81.8% | $0.0078 | 5.8s | 49% |
| 126 | Claude Sonnet 5 (Reasoning, Low) | 94.7% | $0.042 | 26.3s | 68% |
| 127 | Aion 3.0 | 95.9% | $0.035 | 1.4m | 76% |
| 128 | GPT-5.5 (Reasoning) | 96.8% | $0.071 | 30.3s | 90% |
| 129 | Claude Opus 4.8 (Reasoning) | 98.4% | $0.082 | 21.0s | 92% |
| 130 | Claude Opus 4.8 (Reasoning, Low) | 98.1% | $0.080 | 20.4s | 90% |
| 131 | Nemotron 3 Super | 90.9% | $0.0000 | 2.3m | 65% |
| 132 | Grok 4.3 | 78.2% | $0.0061 | 6.1s | 47% |
| 133 | GPT-5.4 Mini | 75.5% | $0.0033 | 3.1s | 47% |
| 134 | DeepSeek V4 Pro 0813 (Reasoning, High) | 93.7% | $0.026 | 1.9m | 76% |
| 135 | Mistral Small 3.2 24B | 72.3% | $0.0006 | 10.4s | 49% |
| 136 | Gemma 4 26B | 83.7% | $0.0006 | 25.0s | 38% |
| 137 | Claude Opus 5 (Reasoning, Low) | 98.1% | $0.070 | 16.6s | 77% |
| 138 | Qwen 2.5 72B | 78.0% | $0.0008 | 13.9s | 41% |
| 139 | DeepSeek V3.1 | 79.4% | $0.0014 | 31.1s | 44% |
| 140 | Laguna S 2.1 | 86.8% | $0.0009 | 1.4m | 49% |
| 141 | Nemotron 3 Nano | 93.5% | $0.0031 | 3.5m | 81% |
| 142 | Qwen 3.6 Max Preview | 98.9% | $0.050 | 2.5m | 94% |
| 143 | GPT-5 Nano | 88.5% | $0.0049 | 1.9m | 57% |
| 144 | Claude Sonnet 5 (Reasoning) | 92.3% | $0.043 | 27.5s | 57% |
| 145 | Claude Sonnet 4.6 (Reasoning) | 95.9% | $0.076 | 51.3s | 87% |
| 146 | GPT-5 | 96.2% | $0.061 | 1.6m | 87% |
| 147 | Claude Opus 5 (Reasoning) | 97.5% | $0.070 | 16.7s | 69% |
| 148 | Claude Sonnet 5 | 83.6% | $0.021 | 9.7s | 41% |
| 149 | Z.AI GLM 5.3 (Reasoning, Max) | 98.6% | $0.045 | 3.1m | 94% |
| 150 | Ministral 3 14B | 67.1% | $0.0010 | 6.3s | 41% |
| 151 | Qwen 3.5 397B A17B | 95.5% | $0.026 | 2.9m | 76% |
| 152 | DeepSeek V4 Pro (Reasoning) | 94.0% | $0.014 | 2.8m | 62% |
| 153 | GPT-4o Mini (temp=1) | 67.1% | $0.0006 | 7.4s | 34% |
| 154 | Llama 3.1 70B | 72.2% | $0.0021 | 24.3s | 32% |
| 155 | Hy4 Preview (Reasoning, High) | 94.1% | $0.036 | 3.2m | 83% |
| 156 | GPT-5.4 Nano (Reasoning) | 77.0% | $0.0035 | 16.6s | 23% |
| 157 | GPT-4o Mini (temp=0) | 69.1% | $0.0006 | 25.0s | 32% |
| 158 | Gemini 2.5 Flash Lite | 64.3% | $0.0005 | 2.3s | 31% |
| 159 | Gemma 3 12B | 62.3% | $0.0003 | 12.0s | 34% |
| 160 | Ministral 3 8B | 58.4% | $0.0007 | 4.8s | 36% |
| 161 | Mistral Small 4 | 56.5% | $0.0008 | 4.3s | 35% |
| 162 | Cydonia 24B V4.1 | 59.1% | $0.0010 | 14.4s | 34% |
| 163 | Thinking Machines Inkling | 68.2% | $0.0077 | 1.0m | 40% |
| 164 | Ministral 3 3B | 56.1% | $0.0005 | 3.3s | 29% |
| 165 | Hermes 3 70B | 60.7% | $0.0013 | 29.2s | 31% |
| 166 | Ministral 8B | 52.4% | $0.0005 | 5.6s | 31% |
| 167 | Ministral 3B | 53.5% | $0.0002 | 2.9s | 28% |
| 168 | Kimi K2.6 | 95.5% | $0.038 | 4.1m | 76% |
| 169 | Claude Opus 4 | 90.4% | $0.116 | 15.8s | 77% |
| 170 | Cohere Command R+ (Aug. 2024) | 60.3% | $0.014 | 10.0s | 24% |
| 171 | Thinking Machines Inkling (Reasoning) | 95.2% | $0.027 | 5.6m | 87% |
| 172 | Mistral NeMO | 44.0% | $0.0007 | 13.3s | 21% |
| 173 | Qwen 3.8 Max (Reasoning, XHigh) | 96.9% | $0.073 | 4.5m | 87% |
| 174 | GPT-5.4 Nano | 35.5% | $0.0008 | 2.9s | 13% |
| 175 | GPT-5.4 Nano (Reasoning, Low) | 43.0% | $0.0013 | 6.1s | 4% |
| 176 | WizardLM 2 8x22b | 32.2% | $0.0036 | 15.7s | 6% |
| 177 | Gemma 3 4B | 20.8% | $0.0002 | 12.5s | 14% |
| 178 | GPT-4.1 Nano | 20.4% | $0.0004 | 3.9s | 0% |
| 179 | Aion 3.0 Mini | 46.5% | $0.0091 | 1.9m | 0% |