| 1 | Gemini 3.1 Flash Lite | 100.0% | $0.0031 | 3.3s | 100% |
| 2 | Gemini 3.1 Flash Lite (Reasoning) | 100.0% | $0.0033 | 3.2s | 100% |
| 3 | Gemini 3.1 Flash Lite (Preview) | 100.0% | $0.0046 | 3.2s | 100% |
| 4 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 100.0% | $0.0057 | 3.2s | 100% |
| 5 | Gemini 3.5 Flash Lite (Reasoning) | 100.0% | $0.0062 | 3.1s | 100% |
| 6 | GPT-5.4 Nano | 100.0% | $0.0026 | 11.2s | 100% |
| 7 | Gemini 2.5 Flash | 100.0% | $0.0075 | 6.1s | 100% |
| 8 | GPT-5.4 Nano (Reasoning, Low) | 100.0% | $0.0038 | 13.8s | 100% |
| 9 | Gemini 3 Flash (Preview) | 100.0% | $0.0087 | 7.1s | 100% |
| 10 | GPT-5.6 Luna | 100.0% | $0.012 | 8.7s | 100% |
| 11 | Inception Mercury 2 | 100.0% | $0.0096 | 12.8s | 100% |
| 12 | DeepSeek V4 Pro | 100.0% | $0.0083 | 17.3s | 100% |
| 13 | GPT-5.4 Mini (Reasoning, Low) | 100.0% | $0.014 | 14.4s | 100% |
| 14 | Grok 4.20 | 100.0% | $0.020 | 7.5s | 100% |
| 15 | Gemini 3.5 Flash (Reasoning, Minimal) | 100.0% | $0.024 | 6.3s | 100% |
| 16 | DeepSeek V3.2 | 100.0% | $0.0046 | 33.9s | 100% |
| 17 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 100.0% | $0.0012 | 42.5s | 100% |
| 18 | MiniMax M2.5 | 100.0% | $0.0036 | 45.0s | 100% |
| 19 | GPT-4o, Aug. 6th (temp=0) | 100.0% | $0.032 | 8.4s | 100% |
| 20 | GPT-5.1 | 100.0% | $0.025 | 17.7s | 100% |
| 21 | GPT-5.4 Nano (Reasoning) | 100.0% | $0.0088 | 41.7s | 100% |
| 22 | GPT-5.6 Luna (Reasoning) | 100.0% | $0.027 | 18.6s | 100% |
| 23 | Muse Spark 1.1 (Reasoning, Minimal) | 100.0% | $0.030 | 18.2s | 100% |
| 24 | GPT-5.4 | 100.0% | $0.033 | 17.4s | 100% |
| 25 | Gemini 2.5 Flash (Reasoning) | 100.0% | $0.023 | 37.3s | 100% |
| 26 | Muse Glimmer 30B (Reasoning, Medium) | 100.0% | $0.0062 | 1.1m | 100% |
| 27 | Qwen 3.6 Flash | 100.0% | $0.015 | 51.7s | 100% |
| 28 | Gemini 3.7 Flash (Reasoning, Medium) | 100.0% | $0.036 | 23.4s | 100% |
| 29 | Grok 4.20 (Reasoning) | 100.0% | $0.027 | 40.0s | 100% |
| 30 | Gemini 3 Flash (Preview, Reasoning) | 100.0% | $0.030 | 40.3s | 100% |
| 31 | Thinking Machines Inkling Small (Reasoning, High) | 100.0% | $0.013 | 1.1m | 100% |
| 32 | ByteDance Seed 1.6 | 100.0% | $0.014 | 1.2m | 100% |
| 33 | Muse Spark 1.2 (Reasoning, Medium) | 100.0% | $0.046 | 29.8s | 100% |
| 34 | Muse Spark 1.1 (Reasoning, Medium) | 100.0% | $0.042 | 35.1s | 100% |
| 35 | o4 Mini | 100.0% | $0.037 | 45.7s | 100% |
| 36 | GPT-5.4 (Reasoning, Low) | 100.0% | $0.053 | 35.5s | 100% |
| 37 | Claude Sonnet 4 | 100.0% | $0.072 | 17.5s | 100% |
| 38 | Gemma 4 31B | 100.0% | $0.0028 | 1.9m | 100% |
| 39 | Xiaomi MIMO v2.5 Pro | 100.0% | $0.0076 | 1.9m | 100% |
| 40 | Gemini 3.8 Flash (Reasoning, Medium) | 100.0% | $0.067 | 42.1s | 100% |
| 41 | Claude Sonnet 4.6 | 100.0% | $0.081 | 23.3s | 100% |
| 42 | GPT-5.2 | 100.0% | $0.062 | 50.7s | 100% |
| 43 | GPT-OSS 120B | 100.0% | $0.0040 | 2.2m | 100% |
| 44 | GPT-5 Mini | 100.0% | $0.019 | 2.0m | 100% |
| 45 | GPT-5 Nano | 100.0% | $0.0080 | 2.2m | 100% |
| 46 | GPT-5.6 Sol | 100.0% | $0.096 | 18.1s | 100% |
| 47 | Kimi K3 (Reasoning, Low) | 100.0% | $0.059 | 1.2m | 100% |
| 48 | o4 Mini High | 100.0% | $0.059 | 1.3m | 100% |
| 49 | Z.AI GLM 5.2 (Reasoning, High) | 100.0% | $0.039 | 1.8m | 100% |
| 50 | DeepSeek V4 Pro (Reasoning) | 100.0% | $0.020 | 2.3m | 100% |
| 51 | Gemini 3.6 Flash (Reasoning) | 100.0% | $0.096 | 41.4s | 100% |
| 52 | GPT-5.5 | 100.0% | $0.105 | 37.1s | 100% |
| 53 | Muse Spark 1.3 (Reasoning, Medium) | 100.0% | $0.055 | 1.9m | 100% |
| 54 | Gemma 4 26B (Reasoning) | 100.0% | $0.0041 | 3.1m | 100% |
| 55 | Gemini 2.5 Pro | 100.0% | $0.099 | 58.2s | 100% |
| 56 | Xiaomi MIMO v2.5 | 97.0% | $0.0027 | 1.1m | 88% |
| 57 | Claude Opus 4.5 | 100.0% | $0.131 | 19.8s | 100% |
| 58 | Laguna S 2.1 | 98.5% | $0.0006 | 2.0m | 91% |
| 59 | Gemini 3.5 Flash (Reasoning) | 100.0% | $0.113 | 49.4s | 100% |
| 60 | Qwen 3.6 27B | 100.0% | $0.034 | 2.7m | 100% |
| 61 | Qwen 3.5 397B A17B | 100.0% | $0.045 | 2.6m | 100% |
| 62 | DeepSeek-V2 Chat | 94.0% | $0.0049 | 34.0s | 85% |
| 63 | Qwen 3.5 35B | 98.5% | $0.015 | 2.0m | 91% |
| 64 | Grok 4.5 (Reasoning, High) | 100.0% | $0.080 | 2.0m | 100% |
| 65 | ByteDance Seed 2.0 Lite | 100.0% | $0.014 | 3.6m | 100% |
| 66 | Claude Opus 4.6 | 100.0% | $0.154 | 31.4s | 100% |
| 67 | Gemma 4 26B | 96.0% | $0.0018 | 27.2s | 76% |
| 68 | MiniMax M2.7 | 96.0% | $0.0063 | 21.4s | 76% |
| 69 | Qwen 3.5 27B | 100.0% | $0.029 | 3.7m | 100% |
| 70 | GPT-4o Mini (temp=1) | 96.0% | $0.0026 | 33.4s | 76% |
| 71 | Qwen 3.5 Plus (2026-02-15) | 100.0% | $0.021 | 3.9m | 100% |
| 72 | Gemini 3.6 Flash (Reasoning, Minimal) | 96.0% | $0.029 | 7.1s | 76% |
| 73 | Qwen 3.7 Max | 100.0% | $0.045 | 3.5m | 100% |
| 74 | Claude Opus 4.7 | 100.0% | $0.182 | 24.3s | 100% |
| 75 | Gemini 2.5 Flash Lite | 93.0% | $0.0023 | 4.8s | 75% |
| 76 | Claude Opus 4.7 (Reasoning) | 100.0% | $0.184 | 25.0s | 100% |
| 77 | GPT-5.6 Terra | 96.0% | $0.034 | 9.4s | 76% |
| 78 | Claude Opus 5 | 100.0% | $0.195 | 26.4s | 100% |
| 79 | DeepSeek V4 Pro 0813 (Reasoning, High) | 100.0% | $0.060 | 3.5m | 100% |
| 80 | GPT-4o, Aug. 6th (temp=1) | 94.5% | $0.029 | 9.1s | 75% |
| 81 | Qwen 3.6 35B | 96.0% | $0.014 | 1.1m | 76% |
| 82 | Qwen 3.8 Flash (Reasoning) | 100.0% | $0.015 | 4.9m | 100% |
| 83 | GPT-5.6 Sol (Reasoning) | 100.0% | $0.186 | 59.0s | 100% |
| 84 | Gemini 3.1 Pro (Preview) | 100.0% | $0.172 | 1.5m | 100% |
| 85 | Mistral Large 3 | 85.0% | $0.0091 | 17.5s | 85% |
| 86 | Kimi K3 (Reasoning, High) | 100.0% | $0.102 | 3.1m | 100% |
| 87 | GPT-5.4 Mini (Reasoning) | 100.0% | $0.117 | 2.8m | 100% |
| 88 | Grok 4.5 (Reasoning, Low) | 96.0% | $0.040 | 49.7s | 76% |
| 89 | Thinking Machines Inkling (Reasoning) | 100.0% | $0.060 | 4.1m | 100% |
| 90 | GPT-5.6 Terra (Reasoning) | 96.0% | $0.060 | 24.2s | 76% |
| 91 | DeepSeek V3 (2024-12-26) | 91.5% | $0.0045 | 40.2s | 75% |
| 92 | Qwen 3.6 Max Preview | 100.0% | $0.084 | 3.7m | 100% |
| 93 | Claude Haiku 4.5 | 85.0% | $0.024 | 8.2s | 85% |
| 94 | DeepSeek V4 Flash (Reasoning) | 97.0% | $0.0041 | 3.5m | 88% |
| 95 | Claude Sonnet 5 (Reasoning) | 100.0% | $0.172 | 1.7m | 100% |
| 96 | Claude Sonnet 5 (Reasoning, Low) | 100.0% | $0.175 | 1.7m | 100% |
| 97 | Mistral Small 4 | 88.0% | $0.0030 | 7.4s | 75% |
| 98 | DeepSeek V4 Flash | 85.0% | $0.0020 | 51.4s | 85% |
| 99 | GPT-5.4 Mini | 92.0% | $0.0087 | 7.9s | 68% |
| 100 | Thinking Machines Inkling | 91.5% | $0.018 | 43.6s | 75% |
| 101 | GPT-4o Mini (temp=0) | 92.0% | $0.0019 | 20.7s | 68% |
| 102 | Qwen 3.5 Flash | 97.0% | $0.0040 | 3.8m | 88% |
| 103 | Hy4 Preview (Reasoning, High) | 100.0% | $0.056 | 4.7m | 100% |
| 104 | Grok 4.6 (Reasoning, High) | 100.0% | $0.104 | 3.7m | 100% |
| 105 | GPT-4.1 Mini | 92.0% | $0.0046 | 26.0s | 68% |
| 106 | Kimi K2.5 | 100.0% | $0.031 | 5.4m | 100% |
| 107 | Mistral Large 2 | 85.0% | $0.037 | 20.5s | 85% |
| 108 | GPT-4.1 | 92.0% | $0.024 | 8.5s | 68% |
| 109 | WizardLM 2 8x22b | 96.0% | $0.0098 | 2.3m | 76% |
| 110 | Claude Opus 5 (Reasoning, Low) | 100.0% | $0.246 | 46.5s | 100% |
| 111 | Claude Opus 5 (Reasoning) | 100.0% | $0.247 | 47.3s | 100% |
| 112 | Z.AI GLM 4.5 | 92.0% | $0.0075 | 48.1s | 68% |
| 113 | Qwen 3.7 Flash (Reasoning) | 92.0% | $0.0017 | 56.4s | 68% |
| 114 | GPT-5.4 (Reasoning) | 100.0% | $0.175 | 2.6m | 100% |
| 115 | Gemini 2.5 Flash Lite (Reasoning) | 92.0% | $0.0073 | 1.0m | 68% |
| 116 | Claude Sonnet 5 | 85.0% | $0.068 | 17.1s | 85% |
| 117 | Kimi K2.6 | 100.0% | $0.082 | 5.0m | 100% |
| 118 | Z.AI GLM 4.5 Air | 94.5% | $0.0071 | 3.2m | 75% |
| 119 | Claude Sonnet 4.5 | 86.5% | $0.077 | 18.6s | 77% |
| 120 | Laguna XS 2.1 | 88.0% | $0.0012 | 41.3s | 63% |
| 121 | GPT-5.5 (Reasoning) | 100.0% | $0.251 | 2.0m | 100% |
| 122 | ByteDance Seed 1.6 Flash | 86.7% | $0.0020 | 34.2s | 62% |
| 123 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 100.0% | $0.0062 | 8.0m | 100% |
| 124 | Z.AI GLM 5 Turbo | 96.0% | $0.044 | 3.6m | 76% |
| 125 | Mistral Small 3.2 24B | 81.5% | $0.0017 | 13.8s | 65% |
| 126 | Ministral 8B | 80.0% | $0.0016 | 15.6s | 68% |
| 127 | Grok 4.3 | 84.0% | $0.0094 | 7.8s | 61% |
| 128 | Qwen 3.5 122B | 96.0% | $0.035 | 4.0m | 76% |
| 129 | Llama 3.1 70B | 84.0% | $0.0064 | 34.0s | 61% |
| 130 | ByteDance Seed 2.0 Mini | 100.0% | $0.0062 | 8.7m | 100% |
| 131 | Grok 4.3 (Reasoning) | 91.0% | $0.013 | 13.9s | 46% |
| 132 | Z.AI GLM 5.1 | 100.0% | $0.081 | 7.3m | 100% |
| 133 | Qwen 3.5 Plus (2026-04-20) | 92.0% | $0.023 | 3.1m | 68% |
| 134 | Ministral 3 8B | 77.5% | $0.0022 | 17.0s | 66% |
| 135 | Qwen 2.5 72B | 84.0% | $0.0056 | 1.2m | 61% |
| 136 | DeepSeek V3.1 | 91.0% | $0.0055 | 52.0s | 46% |
| 137 | Mistral Medium 3.1 | 77.5% | $0.010 | 21.2s | 66% |
| 138 | DeepSeek V4 Flash 0731 (Reasoning, High) | 96.0% | $0.0073 | 5.6m | 76% |
| 139 | Z.AI GLM 4.7 | 92.0% | $0.025 | 3.7m | 68% |
| 140 | GPT-5 | 92.0% | $0.092 | 2.3m | 68% |
| 141 | Z.AI GLM 4.7 Flash | 86.5% | $0.0050 | 2.8m | 64% |
| 142 | MiniMax M3 | 100.0% | $0.036 | 9.3m | 100% |
| 143 | Mistral Small 4 (Reasoning) | 85.0% | $0.0051 | 24.7s | 44% |
| 144 | Z.AI GLM 4.6 | 88.0% | $0.018 | 3.0m | 63% |
| 145 | Claude Opus 4.8 (Reasoning) | 100.0% | $0.381 | 1.9m | 100% |
| 146 | Claude Opus 4.6 (Reasoning) | 100.0% | $0.356 | 2.6m | 100% |
| 147 | Claude Opus 4 | 100.0% | $0.368 | 2.4m | 100% |
| 148 | Arcee AI: Trinity Mini | 88.0% | $0.0037 | 1.9m | 47% |
| 149 | Qwen 3 32B | 84.0% | $0.0042 | 2.9m | 61% |
| 150 | Writer: Palmyra X5 | 80.0% | $0.016 | 18.4s | 48% |
| 151 | GPT-5.5 (Reasoning, Low) | 91.0% | $0.097 | 42.6s | 46% |
| 152 | Qwen 3.5 9B | 96.0% | $0.0040 | 7.8m | 76% |
| 153 | Gemma 3 27B | 77.5% | $0.0016 | 27.5s | 47% |
| 154 | Qwen 3.8 27B (Reasoning, XHigh) | 92.0% | $0.053 | 4.9m | 68% |
| 155 | Hermes 3 405B | 83.0% | $0.015 | 1.0m | 42% |
| 156 | Claude Opus 4.8 (Reasoning, Low) | 98.5% | $0.383 | 1.9m | 91% |
| 157 | Gemma 3 12B | 76.5% | $0.0014 | 30.4s | 44% |
| 158 | Hermes 3 70B | 77.5% | $0.0045 | 42.7s | 40% |
| 159 | Ministral 3B | 70.0% | $0.0007 | 9.8s | 45% |
| 160 | Qwen 3.8 Max (Reasoning, XHigh) | 100.0% | $0.160 | 9.6m | 100% |
| 161 | Ministral 3 3B | 67.5% | $0.0007 | 9.9s | 46% |
| 162 | Mistral NeMO | 60.0% | $0.0024 | 15.4s | 60% |
| 163 | Ministral 3 14B | 67.5% | $0.0031 | 25.4s | 46% |
| 164 | Z.AI GLM 5 | 91.0% | $0.037 | 4.6m | 46% |
| 165 | Gemma 3 4B | 65.0% | $0.0007 | 27.5s | 48% |
| 166 | GPT-4.1 Nano | 64.0% | $0.0009 | 6.9s | 46% |
| 167 | Gemma 4 31B (Reasoning) | 91.0% | $0.0043 | 5.8m | 46% |
| 168 | Z.AI GLM 5.3 (Reasoning, Max) | 100.0% | $0.187 | 10.3m | 100% |
| 169 | Nemotron 3 Nano | 82.0% | $0.0039 | 2.8m | 28% |
| 170 | Cydonia 24B V4.1 | 69.5% | $0.0040 | 1.0m | 28% |
| 171 | Claude Sonnet 4.6 (Reasoning) | 100.0% | $0.448 | 5.9m | 100% |
| 172 | Qwen 3 235B A22B Instruct 2507 | 67.0% | $0.0017 | 1.0m | 29% |
| 173 | Cohere Command R+ (Aug. 2024) | 66.0% | $0.057 | 56.5s | 20% |
| 174 | Aion 2.0 | 73.0% | $0.024 | 3.0m | 18% |
| 175 | Aion 3.0 Mini | 76.0% | $0.030 | 4.9m | 28% |
| 176 | Aion 3.0 | 80.5% | $0.074 | 5.8m | 29% |
| 177 | DeepSeek V3 (2025-03-24) | 50.5% | $0.0037 | 50.3s | 17% |
| 178 | Nemotron 3 Super | 61.0% | $0.0000 | 5.5m | 15% |