| 1 | Ministral 3B | 100.0% | $0.0001 | 8.1s | 100% |
| 2 | Ministral 3 3B | 100.0% | $0.0005 | 11.1s | 100% |
| 3 | Ministral 3 14B | 100.0% | $0.0007 | 11.7s | 100% |
| 4 | Mistral Small 4 | 100.0% | $0.0014 | 18.2s | 100% |
| 5 | Claude Haiku 5.5 (Adaptive) | 100.0% | $0.0018 | 19.3s | 100% |
| 6 | Gemini 3 Flash (Preview) | 100.0% | $0.0078 | 19.6s | 100% |
| 7 | DeepSeek V3 (2025-03-24) | 100.0% | $0.0014 | 39.4s | 100% |
| 8 | Muse Glimmer 30B (Reasoning, Medium) | 100.0% | $0.0038 | 43.4s | 100% |
| 9 | Mistral Medium 3.5 (Reasoning) | 100.0% | $0.018 | 18.0s | 100% |
| 10 | Gemma 4 26B | 100.0% | $0.0009 | 55.1s | 100% |
| 11 | Ministral 8B | 99.8% | $0.0004 | 10.4s | 96% |
| 12 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 99.8% | $0.0035 | 6.3s | 96% |
| 13 | Inception Mercury 2 | 99.8% | $0.0032 | 7.0s | 96% |
| 14 | Gemini 3.5 Flash Lite (Reasoning) | 99.8% | $0.0035 | 6.6s | 96% |
| 15 | Z.AI GLM 4.7 Flash | 100.0% | $0.0017 | 1.2m | 100% |
| 16 | Muse Spark 1.2 (Reasoning, Medium) | 100.0% | $0.018 | 38.3s | 100% |
| 17 | Gemini 3.1 Flash Lite (Reasoning) | 99.8% | $0.0030 | 11.9s | 96% |
| 18 | Gemini 3.1 Flash Lite | 99.8% | $0.0030 | 12.1s | 96% |
| 19 | Ministral 3 8B | 99.8% | $0.0008 | 19.6s | 96% |
| 20 | GPT-5.4 Nano (Reasoning, Low) | 99.8% | $0.0055 | 20.6s | 96% |
| 21 | GPT-6 Luna | 99.8% | $0.0013 | 32.6s | 96% |
| 22 | GPT-4o Mini (temp=1) | 99.8% | $0.0012 | 34.8s | 96% |
| 23 | Gemma 4 31B | 100.0% | $0.0010 | 1.6m | 100% |
| 24 | Arcee AI: Trinity Mini | 99.6% | $0.0003 | 9.2s | 94% |
| 25 | DeepSeek V4.1 Flash (Reasoning, High) | 99.8% | $0.0029 | 35.4s | 96% |
| 26 | Grok 4.5 (Reasoning, Low) | 100.0% | $0.018 | 1.1m | 100% |
| 27 | Gemini 3.1 Flash Lite (Preview) | 99.6% | $0.0030 | 8.4s | 94% |
| 28 | Mistral Medium 3.1 | 99.8% | $0.0048 | 36.5s | 96% |
| 29 | Claude Haiku 5.5 (Reasoning, Low) | 99.6% | $0.0014 | 14.5s | 94% |
| 30 | GPT-OSS 120B | 100.0% | $0.0015 | 1.8m | 100% |
| 31 | Gemini 3.5 Flash (Reasoning, Minimal) | 99.8% | $0.018 | 12.0s | 96% |
| 32 | Gemini 3.6 Flash (Reasoning, Minimal) | 99.8% | $0.017 | 14.3s | 96% |
| 33 | Gemini 2.5 Flash | 99.6% | $0.0052 | 10.6s | 94% |
| 34 | Mistral Medium 3.5 | 99.8% | $0.018 | 18.2s | 96% |
| 35 | DeepSeek V3 (2024-12-26) | 99.8% | $0.0021 | 54.6s | 96% |
| 36 | Thinking Machines Inkling Small (Reasoning, High) | 100.0% | $0.0088 | 1.7m | 100% |
| 37 | GPT-6 Luna (Reasoning, High) | 99.8% | $0.0023 | 57.1s | 96% |
| 38 | GPT-4o, Aug. 6th (temp=1) | 99.8% | $0.018 | 24.4s | 96% |
| 39 | Gemini 2.5 Flash Lite | 99.3% | $0.0009 | 9.5s | 93% |
| 40 | GPT-5.4 Nano (Reasoning) | 99.6% | $0.0061 | 24.5s | 94% |
| 41 | Nemotron 3 Nano | 99.8% | $0.0010 | 1.1m | 96% |
| 42 | Hermes 3 70B | 99.8% | $0.0010 | 1.2m | 96% |
| 43 | Claude Haiku 5.5 (Reasoning, Medium) | 99.3% | $0.0014 | 14.9s | 93% |
| 44 | GPT-5.4 Mini (Reasoning) | 99.8% | $0.022 | 28.1s | 96% |
| 45 | GPT-6 Luna (Reasoning, Medium) | 99.6% | $0.0016 | 43.0s | 94% |
| 46 | GPT-5.4 Mini (Reasoning, Low) | 99.6% | $0.015 | 16.8s | 94% |
| 47 | Gemini 3.8 Flash (Reasoning, Medium) | 99.6% | $0.014 | 18.0s | 94% |
| 48 | GPT-5.4 Mini | 99.6% | $0.015 | 16.8s | 94% |
| 49 | GPT-4.1 Mini | 99.3% | $0.0027 | 19.0s | 93% |
| 50 | Gemini 3 Flash (Preview, Reasoning) | 99.6% | $0.012 | 30.1s | 94% |
| 51 | Qwen 3 32B | 99.6% | $0.0015 | 54.6s | 94% |
| 52 | Llama 3.1 70B | 99.3% | $0.0015 | 29.4s | 93% |
| 53 | Qwen 3 235B A22B Instruct 2507 | 99.6% | $0.0011 | 59.2s | 94% |
| 54 | Mistral Large 3 | 99.3% | $0.0033 | 30.3s | 93% |
| 55 | GPT-5 Nano | 99.8% | $0.0042 | 1.4m | 96% |
| 56 | Cohere Command R+ (Aug. 2024) | 99.8% | $0.020 | 52.5s | 96% |
| 57 | Z.AI GLM 4.6 | 99.6% | $0.0065 | 51.5s | 94% |
| 58 | Qwen 3.5 Plus (2026-02-15) | 99.3% | $0.0060 | 31.5s | 93% |
| 59 | Gemini 3.7 Flash (Reasoning, Medium) | 99.3% | $0.012 | 18.2s | 93% |
| 60 | GPT-4o, Aug. 6th (temp=0) | 99.6% | $0.023 | 22.7s | 94% |
| 61 | GPT-5.6 Luna | 99.3% | $0.015 | 15.8s | 93% |
| 62 | GPT-5 Mini | 99.6% | $0.0100 | 57.4s | 94% |
| 63 | GPT-5.6 Luna (Reasoning, Medium) | 99.3% | $0.017 | 18.0s | 93% |
| 64 | Mistral Large 4.0 | 99.6% | $0.0063 | 1.1m | 94% |
| 65 | DeepSeek-V2 Chat | 99.3% | $0.0021 | 53.3s | 93% |
| 66 | Z.AI GLM 5.2 (Reasoning, High) | 99.6% | $0.011 | 1.0m | 94% |
| 67 | Qwen 3.5 9B | 99.6% | $0.0011 | 1.4m | 94% |
| 68 | Hermes 3 405B | 99.3% | $0.0032 | 53.2s | 93% |
| 69 | Nemotron 3 Super | 99.6% | $0.0000 | 1.4m | 94% |
| 70 | GPT-5.4 Nano | 99.1% | $0.0057 | 26.3s | 92% |
| 71 | Qwen 2.5 72B | 99.1% | $0.0010 | 36.7s | 92% |
| 72 | Gemini 2.5 Flash (Reasoning) | 99.1% | $0.011 | 21.5s | 92% |
| 73 | Gemma 4 26B (Reasoning) | 99.8% | $0.0013 | 2.0m | 96% |
| 74 | Gemini 3.6 Flash (Reasoning) | 99.8% | $0.044 | 32.5s | 96% |
| 75 | Gemini 3.5 Flash (Reasoning) | 100.0% | $0.071 | 37.6s | 100% |
| 76 | Qwen 3.5 35B | 99.6% | $0.018 | 1.0m | 94% |
| 77 | Qwen 3.5 Flash | 99.1% | $0.0025 | 47.5s | 92% |
| 78 | o4 Mini High | 99.6% | $0.025 | 47.2s | 94% |
| 79 | Z.AI GLM 4.5 | 99.1% | $0.0051 | 42.1s | 92% |
| 80 | Gemma 4 31B (Reasoning) | 99.8% | $0.0014 | 2.2m | 96% |
| 81 | GPT-4.1 Nano | 98.7% | $0.0007 | 13.3s | 90% |
| 82 | Qwen 3.6 35B | 99.3% | $0.0083 | 1.0m | 93% |
| 83 | Mistral Small 4 (Reasoning) | 98.9% | $0.0022 | 30.2s | 91% |
| 84 | Mistral Large 2 | 99.1% | $0.013 | 29.4s | 92% |
| 85 | Qwen 3.7 Flash (Reasoning) | 99.1% | $0.0010 | 55.2s | 92% |
| 86 | Gemini 2.5 Flash Lite (Reasoning) | 98.9% | $0.0028 | 30.8s | 91% |
| 87 | Z.AI GLM 4.7 | 99.6% | $0.010 | 1.4m | 94% |
| 88 | o4 Mini | 99.3% | $0.015 | 25.7s | 91% |
| 89 | Writer: Palmyra X5 | 98.9% | $0.011 | 22.0s | 91% |
| 90 | Qwen 3.5 122B | 99.6% | $0.025 | 1.1m | 94% |
| 91 | DeepSeek V4 Flash (Reasoning) | 98.7% | $0.0007 | 31.1s | 90% |
| 92 | Claude Sonnet 5.5 (Reasoning) | 99.6% | $0.042 | 36.9s | 94% |
| 93 | GPT-4o Mini (temp=0) | 98.7% | $0.0012 | 34.8s | 90% |
| 94 | Grok 4.5 (Reasoning, High) | 99.8% | $0.030 | 1.6m | 96% |
| 95 | Grok 4.3 | 98.7% | $0.0069 | 30.5s | 90% |
| 96 | Qwen 3.6 Flash | 99.1% | $0.010 | 41.4s | 90% |
| 97 | DeepSeek V3.1 | 99.3% | $0.0020 | 1.8m | 93% |
| 98 | Qwen 3.5 Plus (2026-04-20) | 99.6% | $0.017 | 1.8m | 94% |
| 99 | ByteDance Seed 1.6 | 99.8% | $0.013 | 2.5m | 96% |
| 100 | Grok 4.6 (Reasoning, High) | 100.0% | $0.042 | 2.5m | 100% |
| 101 | Thinking Machines Inkling | 99.1% | $0.0075 | 1.5m | 92% |
| 102 | GPT-5.6 Terra (Reasoning, Medium) | 99.3% | $0.044 | 35.2s | 93% |
| 103 | Aion 2.0 | 98.9% | $0.0064 | 1.3m | 91% |
| 104 | Gemma 3 27B | 98.4% | $0.0006 | 52.6s | 89% |
| 105 | GPT-6.1 Sol (Reasoning, Medium) | 99.6% | $0.031 | 1.6m | 94% |
| 106 | WizardLM 2 8x22b | 99.1% | $0.0026 | 1.8m | 92% |
| 107 | Muse Spark 1.1 (Reasoning, Medium) | 98.4% | $0.015 | 23.9s | 89% |
| 108 | Mistral NeMO | 97.8% | $0.0005 | 10.1s | 87% |
| 109 | Z.AI GLM 4.5 Air | 98.7% | $0.0029 | 58.2s | 88% |
| 110 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 98.4% | $0.0005 | 1.1m | 89% |
| 111 | Grok 4.20 (Reasoning) | 99.1% | $0.018 | 1.5m | 92% |
| 112 | Xiaomi MIMO v2.6 Flash | 98.9% | $0.0008 | 1.8m | 91% |
| 113 | ByteDance Seed 2.0 Lite | 99.3% | $0.012 | 2.2m | 93% |
| 114 | Muse Spark 1.3 (Reasoning, Medium) | 99.3% | $0.025 | 1.8m | 93% |
| 115 | Qwen 3.5 27B | 99.3% | $0.020 | 1.6m | 91% |
| 116 | Claude Sonnet 5 (Reasoning, Low) | 98.7% | $0.031 | 38.4s | 90% |
| 117 | Kimi K3 (Reasoning, Low) | 98.9% | $0.028 | 1.1m | 91% |
| 118 | Claude Sonnet 4.6 (Reasoning) | 99.6% | $0.060 | 1.2m | 94% |
| 119 | Qwen 3.8 Flash (Reasoning) | 99.6% | $0.0064 | 3.1m | 94% |
| 120 | Xiaomi MIMO v2.5 | 98.0% | $0.0054 | 31.8s | 87% |
| 121 | Muse Spark 1.1 (Reasoning, Minimal) | 97.8% | $0.012 | 19.2s | 87% |
| 122 | Cydonia 24B V4.1 | 98.0% | $0.0014 | 44.8s | 87% |
| 123 | GPT-4.1 | 98.2% | $0.018 | 44.7s | 89% |
| 124 | Grok 4.3 (Reasoning) | 99.3% | $0.021 | 2.3m | 93% |
| 125 | Aion 3.5 (Reasoning, High) | 98.7% | $0.022 | 1.3m | 90% |
| 126 | Claude Sonnet 4.6 | 98.4% | $0.031 | 39.3s | 89% |
| 127 | Laguna S 2.1 | 97.3% | $0.0005 | 22.1s | 86% |
| 128 | GPT-6 Sol (Reasoning, Medium) | 98.7% | $0.031 | 1.0m | 90% |
| 129 | GPT-6 Sol | 98.4% | $0.027 | 51.4s | 89% |
| 130 | Xiaomi MIMO v2.6 Pro | 98.9% | $0.0033 | 2.0m | 89% |
| 131 | Claude Opus 5.5 (Reasoning) | 99.8% | $0.092 | 56.0s | 96% |
| 132 | GPT-5.6 Terra | 98.7% | $0.046 | 36.9s | 90% |
| 133 | Mistral Large 4.0 (Reasoning) | 99.8% | $0.023 | 3.4m | 96% |
| 134 | DeepSeek V3.2 | 98.7% | $0.0014 | 1.9m | 88% |
| 135 | MiniMax M2.5 | 98.0% | $0.0034 | 1.3m | 88% |
| 136 | Claude Sonnet 5 (Reasoning) | 98.2% | $0.030 | 38.9s | 89% |
| 137 | DeepSeek V4 Pro 0813 (Reasoning, High) | 98.9% | $0.025 | 1.8m | 91% |
| 138 | Qwen 3.5 397B A17B | 99.3% | $0.014 | 3.0m | 93% |
| 139 | GPT-5.2 | 99.3% | $0.056 | 1.5m | 93% |
| 140 | Gemini 2.5 Pro | 98.2% | $0.036 | 36.2s | 89% |
| 141 | Gemini 3.1 Pro (Preview) | 100.0% | $0.107 | 1.8m | 100% |
| 142 | MiniMax M3 | 99.1% | $0.0060 | 3.1m | 92% |
| 143 | Hy4 Preview (Reasoning, High) | 100.0% | $0.040 | 4.4m | 100% |
| 144 | Aion 3.5 Mini (Reasoning, High) | 98.9% | $0.011 | 2.4m | 89% |
| 145 | Qwen 3.6 27B | 98.9% | $0.025 | 2.3m | 91% |
| 146 | Claude Opus 4.8 (Reasoning, Low) | 98.9% | $0.071 | 41.9s | 91% |
| 147 | ByteDance Seed 1.6 Flash | 96.9% | $0.0013 | 27.3s | 84% |
| 148 | Claude Opus 5 (Reasoning, Low) | 99.6% | $0.097 | 1.0m | 94% |
| 149 | ByteDance Seed 2.0 Mini | 99.8% | $0.0045 | 4.9m | 96% |
| 150 | GPT-5.4 | 98.7% | $0.049 | 1.4m | 90% |
| 151 | Claude Opus 4.7 (Reasoning) | 98.7% | $0.076 | 32.0s | 90% |
| 152 | Qwen 3.6 Max Preview | 99.8% | $0.050 | 3.5m | 96% |
| 153 | GPT-5.4 (Reasoning, Low) | 98.9% | $0.055 | 1.4m | 89% |
| 154 | Claude Opus 5 | 98.9% | $0.082 | 50.1s | 91% |
| 155 | Claude Opus 5 (Reasoning) | 99.3% | $0.098 | 1.0m | 93% |
| 156 | Laguna XS 2.1 | 96.4% | $0.0003 | 14.4s | 83% |
| 157 | Xiaomi MIMO v2.5 Pro | 97.1% | $0.0085 | 53.5s | 85% |
| 158 | Gemma 3 12B | 96.4% | $0.0004 | 41.3s | 85% |
| 159 | Claude Sonnet 5 | 97.1% | $0.027 | 33.5s | 86% |
| 160 | Grok 4.7 (Reasoning, High) | 100.0% | $0.074 | 3.9m | 100% |
| 161 | Claude Opus 4.7 | 98.2% | $0.069 | 30.4s | 89% |
| 162 | Claude Opus 4.6 | 98.9% | $0.078 | 1.2m | 91% |
| 163 | MiniMax M2.7 | 97.3% | $0.0040 | 1.1m | 83% |
| 164 | Z.AI GLM 5 Turbo | 96.7% | $0.0081 | 33.2s | 83% |
| 165 | Claude Opus 4.6 (Reasoning) | 99.1% | $0.088 | 1.4m | 92% |
| 166 | Grok 4.20 | 96.4% | $0.0093 | 45.7s | 85% |
| 167 | Claude Opus 4.8 (Reasoning) | 98.2% | $0.071 | 41.7s | 89% |
| 168 | Aion 3.0 | 97.3% | $0.024 | 1.0m | 85% |
| 169 | Gemma 3 4B | 95.6% | $0.0002 | 20.0s | 83% |
| 170 | Kimi K3 (Reasoning, High) | 98.2% | $0.044 | 1.8m | 89% |
| 171 | Thinking Machines Inkling (Reasoning) | 99.8% | $0.025 | 5.1m | 96% |
| 172 | DeepSeek V4 Flash 0731 (Reasoning, High) | 98.4% | $0.0022 | 2.6m | 84% |
| 173 | DeepSeek V4 Flash | 96.4% | $0.0006 | 31.6s | 81% |
| 174 | Kimi K2.5 | 98.7% | $0.019 | 3.2m | 88% |
| 175 | DeepSeek V4 Pro (Reasoning) | 98.4% | $0.015 | 3.1m | 88% |
| 176 | GPT-5.4 (Reasoning) | 99.6% | $0.089 | 2.6m | 94% |
| 177 | GPT-5.1 | 98.2% | $0.054 | 1.8m | 89% |
| 178 | Claude Haiku 4.5 | 96.0% | $0.011 | 21.6s | 82% |
| 179 | Qwen 3.7 Max | 98.9% | $0.068 | 2.3m | 91% |
| 180 | Mistral Small 3.2 24B | 99.6% | $0.0070 | 5.7m | 94% |
| 181 | Qwen 3.8 27B (Reasoning, XHigh) | 99.6% | $0.040 | 4.7m | 94% |
| 182 | Aion 3.0 Mini | 96.2% | $0.0053 | 1.2m | 82% |
| 183 | GPT-5.6 Sol (Reasoning, Medium) | 98.7% | $0.108 | 1.2m | 90% |
| 184 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 99.6% | $0.0031 | 6.5m | 94% |
| 185 | GPT-5 | 98.7% | $0.065 | 2.8m | 90% |
| 186 | GPT-5.6 Sol | 98.0% | $0.105 | 1.2m | 88% |
| 187 | Z.AI GLM 5.1 | 96.2% | $0.014 | 1.5m | 80% |
| 188 | Qwen 3.8 Max (Reasoning, XHigh) | 100.0% | $0.083 | 5.9m | 100% |
| 189 | Claude Sonnet 4.5 | 95.8% | $0.035 | 38.1s | 81% |
| 190 | GPT-5.5 (Reasoning, Medium) | 99.1% | $0.142 | 1.8m | 92% |
| 191 | Claude Haiku 5.5 (Reasoning, Max) | 100.0% | $0.049 | 7.5m | 100% |
| 192 | DeepSeek V4 Pro | 95.1% | $0.0048 | 1.3m | 79% |
| 193 | Claude Sonnet 4 | 94.4% | $0.032 | 43.7s | 78% |
| 194 | Kimi K2.6 | 99.3% | $0.058 | 6.5m | 93% |
| 195 | Z.AI GLM 5 | 94.4% | $0.0084 | 1.2m | 75% |
| 196 | GPT-5.5 | 96.9% | $0.139 | 1.7m | 84% |
| 197 | Claude Opus 4.5 | 94.7% | $0.070 | 53.4s | 76% |
| 198 | GPT-5.5 (Reasoning, Low) | 96.7% | $0.139 | 1.8m | 83% |
| 199 | Z.AI GLM 5.3 (Reasoning, Max) | 98.4% | $0.066 | 7.3m | 88% |
| 200 | Claude Opus 4 | 90.0% | $0.209 | 1.4m | 64% |