| 1 | Gemini 3.1 Flash Lite (Reasoning) | 100.0% | $0.0033 | 3.2s | 100% |
| 2 | Gemini 3.1 Flash Lite (Preview) | 100.0% | $0.0046 | 3.2s | 100% |
| 3 | Gemma 3 12B | 100.0% | $0.0014 | 30.4s | 100% |
| 4 | Gemma 4 26B | 96.6% | $0.0018 | 27.2s | 89% |
| 5 | Gemini 2.5 Flash | 94.5% | $0.0075 | 6.1s | 82% |
| 6 | Qwen 3.6 35B | 98.4% | $0.014 | 1.1m | 90% |
| 7 | Qwen 3.6 Flash | 97.1% | $0.015 | 51.7s | 88% |
| 8 | GPT-5.4 (Reasoning, Low) | 97.0% | $0.053 | 35.5s | 85% |
| 9 | Claude Sonnet 4 | 97.3% | $0.072 | 17.5s | 84% |
| 10 | Claude Sonnet 4.5 | 95.3% | $0.077 | 18.6s | 85% |
| 11 | GPT-5.6 Terra | 92.1% | $0.034 | 9.4s | 76% |
| 12 | GPT-5 Mini | 96.0% | $0.019 | 2.0m | 86% |
| 13 | GPT-5 | 100.0% | $0.092 | 2.3m | 100% |
| 14 | GPT-5.4 Mini (Reasoning, Low) | 88.9% | $0.014 | 14.4s | 68% |
| 15 | GPT-5.2 | 94.5% | $0.062 | 50.7s | 78% |
| 16 | GPT-5.4 Nano (Reasoning) | 88.4% | $0.0088 | 41.7s | 71% |
| 17 | Xiaomi MIMO v2.5 | 88.4% | $0.0027 | 1.1m | 69% |
| 18 | o4 Mini High | 91.7% | $0.059 | 1.3m | 77% |
| 19 | DeepSeek V4 Pro (Reasoning) | 93.1% | $0.020 | 2.3m | 77% |
| 20 | Gemini 3 Flash (Preview) | 83.8% | $0.0087 | 7.1s | 56% |
| 21 | Gemini 3.1 Flash Lite | 88.2% | $0.0031 | 3.3s | 49% |
| 22 | Claude Opus 4.5 | 92.4% | $0.131 | 19.8s | 75% |
| 23 | GPT-5.6 Terra (Reasoning) | 86.4% | $0.060 | 24.2s | 65% |
| 24 | Z.AI GLM 5.2 (Reasoning, High) | 89.8% | $0.039 | 1.8m | 71% |
| 25 | Nemotron 3 Nano | 93.1% | $0.0039 | 2.8m | 71% |
| 26 | Grok 4.20 (Reasoning) | 85.4% | $0.027 | 40.0s | 58% |
| 27 | Claude Sonnet 4.6 | 84.6% | $0.081 | 23.3s | 66% |
| 28 | GPT-5.4 | 80.9% | $0.033 | 17.4s | 57% |
| 29 | Grok 4.3 | 80.0% | $0.0094 | 7.8s | 50% |
| 30 | o4 Mini | 85.4% | $0.037 | 45.7s | 57% |
| 31 | Mistral Large 3 | 78.2% | $0.0091 | 17.5s | 52% |
| 32 | Grok 4.3 (Reasoning) | 84.6% | $0.013 | 13.9s | 44% |
| 33 | Qwen 3.5 35B | 87.4% | $0.015 | 2.0m | 60% |
| 34 | Xiaomi MIMO v2.5 Pro | 84.8% | $0.0076 | 1.9m | 60% |
| 35 | GPT-5.4 Mini (Reasoning) | 95.6% | $0.117 | 2.8m | 82% |
| 36 | GPT-5.6 Luna (Reasoning) | 81.0% | $0.027 | 18.6s | 51% |
| 37 | Qwen 3.5 Plus (2026-04-20) | 90.3% | $0.023 | 3.1m | 70% |
| 38 | GPT-4o Mini (temp=0) | 80.0% | $0.0019 | 20.7s | 46% |
| 39 | Qwen3.6 Max Preview | 95.0% | $0.084 | 3.7m | 84% |
| 40 | Grok 4.5 (Reasoning, Low) | 82.6% | $0.040 | 49.7s | 55% |
| 41 | GPT-OSS 120B | 83.2% | $0.0040 | 2.2m | 58% |
| 42 | Gemini 2.5 Flash (Reasoning) | 82.4% | $0.023 | 37.3s | 45% |
| 43 | Qwen 3.5 122B | 91.0% | $0.035 | 4.0m | 75% |
| 44 | DeepSeek V4 Pro | 78.5% | $0.0083 | 17.3s | 40% |
| 45 | Claude Sonnet 5 | 80.8% | $0.068 | 17.1s | 51% |
| 46 | DeepSeek V4 Flash | 79.7% | $0.0020 | 51.4s | 43% |
| 47 | GPT-5.5 (Reasoning, Low) | 82.0% | $0.097 | 42.6s | 60% |
| 48 | GPT-4o, Aug. 6th (temp=0) | 83.1% | $0.032 | 8.4s | 36% |
| 49 | Inception Mercury 2 | 74.8% | $0.0096 | 12.8s | 39% |
| 50 | Claude Opus 4.6 | 83.7% | $0.154 | 31.4s | 64% |
| 51 | Qwen 3.6 27B | 87.7% | $0.034 | 2.7m | 56% |
| 52 | GPT-5.6 Sol | 80.7% | $0.096 | 18.1s | 51% |
| 53 | DeepSeek V3.2 | 73.5% | $0.0046 | 33.9s | 41% |
| 54 | Claude Sonnet 5 (Reasoning) | 90.4% | $0.172 | 1.7m | 73% |
| 55 | Gemma 4 26B (Reasoning) | 89.1% | $0.0041 | 3.1m | 50% |
| 56 | Z.AI GLM 4.5 | 74.3% | $0.0075 | 48.1s | 39% |
| 57 | Qwen 3.5 Plus (2026-02-15) | 87.6% | $0.021 | 3.9m | 58% |
| 58 | Claude Opus 4.7 | 84.4% | $0.182 | 24.3s | 59% |
| 59 | Gemma 4 31B (Reasoning) | 93.1% | $0.0043 | 5.8m | 69% |
| 60 | Z.AI GLM 5 | 90.4% | $0.037 | 4.6m | 64% |
| 61 | Gemma 4 31B | 75.5% | $0.0028 | 1.9m | 44% |
| 62 | Mistral Large 2 | 70.1% | $0.037 | 20.5s | 37% |
| 63 | Z.AI GLM 5 Turbo | 83.6% | $0.044 | 3.6m | 57% |
| 64 | Aion 2.0 | 80.6% | $0.024 | 3.0m | 49% |
| 65 | Claude Sonnet 5 (Reasoning, Low) | 85.3% | $0.175 | 1.7m | 63% |
| 66 | Z.AI GLM 4.5 Air | 80.9% | $0.0071 | 3.2m | 46% |
| 67 | ByteDance Seed 1.6 | 71.4% | $0.014 | 1.2m | 35% |
| 68 | Qwen 3.5 Flash | 79.6% | $0.0040 | 3.8m | 51% |
| 69 | Claude Opus 4.7 (Reasoning) | 84.7% | $0.184 | 25.0s | 49% |
| 70 | GPT-4o Mini (temp=1) | 63.8% | $0.0026 | 33.4s | 31% |
| 71 | GPT-5.4 Nano (Reasoning, Low) | 59.2% | $0.0038 | 13.8s | 31% |
| 72 | Claude Haiku 4.5 | 67.7% | $0.024 | 8.2s | 25% |
| 73 | Llama 3.1 70B | 61.5% | $0.0064 | 34.0s | 32% |
| 74 | DeepSeek-V2 Chat | 71.6% | $0.0049 | 34.0s | 20% |
| 75 | DeepSeek V3 (2025-03-24) | 69.2% | $0.0037 | 50.3s | 23% |
| 76 | Gemini 3 Flash (Preview, Reasoning) | 67.5% | $0.030 | 40.3s | 27% |
| 77 | DeepSeek V3.1 | 71.1% | $0.0055 | 52.0s | 19% |
| 78 | Gemini 2.5 Pro | 76.7% | $0.099 | 58.2s | 35% |
| 79 | Gemini 3.5 Flash (Reasoning) | 72.9% | $0.113 | 49.4s | 37% |
| 80 | Aion 3.0 | 87.3% | $0.074 | 5.8m | 67% |
| 81 | Claude Opus 4 | 96.6% | $0.368 | 2.4m | 86% |
| 82 | Gemini 3.5 Flash (Reasoning, Minimal) | 62.4% | $0.024 | 6.3s | 20% |
| 83 | GPT-5.5 | 66.6% | $0.105 | 37.1s | 37% |
| 84 | ByteDance Seed 2.0 Lite | 81.0% | $0.014 | 3.6m | 31% |
| 85 | GPT-4o, Aug. 6th (temp=1) | 58.8% | $0.029 | 9.1s | 20% |
| 86 | Qwen 3 32B | 70.0% | $0.0042 | 2.9m | 31% |
| 87 | Qwen 3.5 397B A17B | 72.1% | $0.045 | 2.6m | 35% |
| 88 | GPT-4.1 | 57.6% | $0.024 | 8.5s | 19% |
| 89 | GPT-4.1 Mini | 52.4% | $0.0046 | 26.0s | 19% |
| 90 | ByteDance Seed 2.0 Mini | 88.8% | $0.0062 | 8.7m | 70% |
| 91 | Mistral Small 4 | 56.1% | $0.0030 | 7.4s | 11% |
| 92 | GPT-5 Nano | 63.4% | $0.0080 | 2.2m | 27% |
| 93 | Qwen 3.5 27B | 71.5% | $0.029 | 3.7m | 39% |
| 94 | Hermes 3 70B | 59.5% | $0.0045 | 42.7s | 14% |
| 95 | Gemma 3 27B | 53.1% | $0.0016 | 27.5s | 15% |
| 96 | GPT-5.4 Mini | 43.1% | $0.0087 | 7.9s | 22% |
| 97 | GPT-5.1 | 51.0% | $0.025 | 17.7s | 17% |
| 98 | GPT-5.6 Luna | 43.9% | $0.012 | 8.7s | 20% |
| 99 | Mistral Small 4 (Reasoning) | 49.2% | $0.0051 | 24.7s | 15% |
| 100 | DeepSeek V4 Flash (Reasoning) | 65.0% | $0.0041 | 3.5m | 28% |
| 101 | DeepSeek V3 (2024-12-26) | 49.0% | $0.0045 | 40.2s | 14% |
| 102 | Cohere Command R+ (Aug. 2024) | 61.3% | $0.057 | 56.5s | 14% |
| 103 | Grok 4.5 (Reasoning, High) | 56.8% | $0.080 | 2.0m | 33% |
| 104 | Z.AI GLM 5.1 | 85.1% | $0.081 | 7.3m | 59% |
| 105 | Writer: Palmyra X5 | 41.8% | $0.016 | 18.4s | 14% |
| 106 | MiniMax M2.7 | 42.5% | $0.0063 | 21.4s | 10% |
| 107 | MoonshotAI: Kimi K2.6 | 75.1% | $0.082 | 5.0m | 42% |
| 108 | Aion 3.0 Mini | 75.1% | $0.030 | 4.9m | 29% |
| 109 | Qwen3 235B A22B Instruct 2507 | 41.7% | $0.0017 | 1.0m | 15% |
| 110 | Claude Opus 4.8 (Reasoning) | 85.2% | $0.381 | 1.9m | 64% |
| 111 | ByteDance Seed 1.6 Flash | 40.9% | $0.0020 | 34.2s | 9% |
| 112 | GPT-5.6 Sol (Reasoning) | 68.2% | $0.186 | 59.0s | 25% |
| 113 | Qwen 2.5 72B | 47.0% | $0.0056 | 1.2m | 7% |
| 114 | GPT-5.4 (Reasoning) | 67.5% | $0.175 | 2.6m | 38% |
| 115 | Z.AI GLM 4.7 Flash | 44.8% | $0.0050 | 2.8m | 25% |
| 116 | MoonshotAI: Kimi K2.5 | 70.6% | $0.031 | 5.4m | 32% |
| 117 | Grok 4.20 | 30.5% | $0.020 | 7.5s | 14% |
| 118 | Qwen3.7 Max | 60.2% | $0.045 | 3.5m | 26% |
| 119 | Ministral 3 8B | 34.5% | $0.0022 | 17.0s | 7% |
| 120 | GPT-5.4 Nano | 21.8% | $0.0026 | 11.2s | 18% |
| 121 | MiniMax M2.5 | 27.1% | $0.0036 | 45.0s | 18% |
| 122 | GPT-4.1 Nano | 22.8% | $0.0009 | 6.9s | 12% |
| 123 | Ministral 8B | 29.3% | $0.0016 | 15.6s | 7% |
| 124 | Gemini 2.5 Flash Lite (Reasoning) | 37.6% | $0.0073 | 1.0m | 7% |
| 125 | Nemotron 3 Super | 66.5% | $0.0000 | 5.5m | 22% |
| 126 | Hermes 3 405B | 38.0% | $0.015 | 1.0m | 7% |
| 127 | GPT-5.5 (Reasoning) | 68.3% | $0.251 | 2.0m | 35% |
| 128 | Claude Opus 4.6 (Reasoning) | 78.4% | $0.356 | 2.6m | 54% |
| 129 | Z.AI GLM 4.7 | 47.3% | $0.025 | 3.7m | 22% |
| 130 | WizardLM 2 8x22b | 44.7% | $0.0098 | 2.3m | 6% |
| 131 | Z.AI GLM 4.6 | 45.0% | $0.018 | 3.0m | 15% |
| 132 | Gemini 2.5 Flash Lite | 23.6% | $0.0023 | 4.8s | 2% |
| 133 | Ministral 3 14B | 19.3% | $0.0031 | 25.4s | 9% |
| 134 | Mistral Medium 3.1 | 18.1% | $0.010 | 21.2s | 7% |
| 135 | Cydonia 24B V4.1 | 26.6% | $0.0040 | 1.0m | 3% |
| 136 | Mistral Small 3.2 24B | 18.3% | $0.0017 | 13.8s | 3% |
| 137 | Arcee AI: Trinity Mini | 32.6% | $0.0037 | 1.9m | 4% |
| 138 | Gemini 3.1 Pro (Preview) | 47.8% | $0.172 | 1.5m | 16% |
| 139 | Ministral 3B | 7.4% | $0.0007 | 9.8s | 4% |
| 140 | Ministral 3 3B | 6.6% | $0.0007 | 9.9s | 3% |
| 141 | Claude Opus 4.8 (Reasoning, Low) | 73.7% | $0.383 | 1.9m | 34% |
| 142 | Mistral NeMO | 4.4% | $0.0024 | 15.4s | 3% |
| 143 | Claude Sonnet 4.6 (Reasoning) | 89.8% | $0.448 | 5.9m | 70% |
| 144 | Gemma 3 4B | 3.2% | $0.0007 | 27.5s | 2% |
| 145 | Qwen 3.5 9B | 55.6% | $0.0040 | 7.8m | 23% |
| 146 | MiniMax M3 | 55.9% | $0.036 | 9.3m | 22% |