Overall Performance
Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Price-Performance Score Distribution (Top 20)
Click a model name to view its detail page.
Most Stable Models (Top 20)
Ranked by stability (median × consistency). Click a model name to view its detail page.
Top Overall Models (Top 20)
Ranked by composite score (performance, cost, speed & stability). Click a model name to view its detail page.
| Rank ▲ | Model | Score | Avg. Cost | Avg. Time | Stability |
|---|---|---|---|---|---|
| 1 | Writer: Palmyra X5 | 83.2% | $0.011 | 22.0s | 50% |
| 2 | Qwen 3 235B A22B Instruct 2507 | 81.0% | $0.0011 | 59.2s | 48% |
| 3 | Qwen 3.7 Flash (Reasoning) | 80.5% | $0.0010 | 55.2s | 46% |
| 4 | GPT-5.4 | 70.2% | $0.049 | 1.4m | 39% |
| 5 | Mistral Small 4 (Reasoning) | 60.6% | $0.0022 | 30.2s | 25% |
| 6 | Mistral Small 4 | 56.1% | $0.0014 | 18.2s | 24% |
| 7 | DeepSeek V4.1 Flash (Reasoning, High) | 57.7% | $0.0029 | 35.4s | 24% |
| 8 | GPT-5.4 (Reasoning, Low) | 67.7% | $0.055 | 1.4m | 36% |
| 9 | Ministral 3 14B | 50.5% | $0.0007 | 11.7s | 25% |
| 10 | Cydonia 24B V4.1 | 61.6% | $0.0014 | 44.8s | 21% |
| 11 | Claude Sonnet 4.5 | 63.6% | $0.035 | 38.1s | 27% |
| 12 | Z.AI GLM 5 | 58.9% | $0.0084 | 1.2m | 26% |
| 13 | Z.AI GLM 5.2 (Reasoning, High) | 55.7% | $0.011 | 1.0m | 25% |
| 14 | GPT-5.4 Mini | 50.0% | $0.015 | 16.8s | 25% |
| 15 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 54.6% | $0.0005 | 1.1m | 23% |
| 16 | Muse Spark 1.1 (Reasoning, Minimal) | 52.1% | $0.012 | 19.2s | 22% |
| 17 | Claude Haiku 4.5 | 52.5% | $0.011 | 21.6s | 21% |
| 18 | Hermes 3 70B | 57.9% | $0.0010 | 1.2m | 20% |
| 19 | Z.AI GLM 5 Turbo | 49.6% | $0.0081 | 33.2s | 22% |
| 20 | Laguna S 2.1 | 45.7% | $0.0005 | 22.1s | 21% |
| 21 | Grok 4.20 | 45.9% | $0.0093 | 45.7s | 26% |
| 22 | GPT-5.4 Mini (Reasoning, Low) | 47.8% | $0.015 | 16.8s | 23% |
| 23 | MiniMax M2.5 | 52.7% | $0.0034 | 1.3m | 23% |
| 24 | Mistral Medium 3.1 | 43.3% | $0.0048 | 36.5s | 25% |
| 25 | Grok 4.5 (Reasoning, Low) | 52.1% | $0.018 | 1.1m | 26% |
| 26 | Claude Haiku 5.5 (Reasoning, Medium) | 46.4% | $0.0014 | 14.9s | 19% |
| 27 | Grok 4.5 (Reasoning, High) | 56.8% | $0.030 | 1.6m | 28% |
| 28 | Hermes 3 405B | 53.5% | $0.0032 | 53.2s | 19% |
| 29 | DeepSeek V4 Pro | 51.0% | $0.0048 | 1.3m | 23% |
| 30 | Claude Haiku 5.5 (Reasoning, Low) | 46.1% | $0.0014 | 14.5s | 18% |
| 31 | Aion 3.5 (Reasoning, High) | 55.2% | $0.022 | 1.3m | 23% |
| 32 | Laguna XS 2.1 | 44.2% | $0.0003 | 14.4s | 18% |
| 33 | Claude Opus 5 | 67.0% | $0.082 | 50.1s | 27% |
| 34 | Muse Spark 1.1 (Reasoning, Medium) | 50.0% | $0.015 | 23.9s | 18% |
| 35 | Claude Opus 4.7 | 60.1% | $0.069 | 30.4s | 26% |
| 36 | Xiaomi MIMO v2.6 Pro | 56.1% | $0.0033 | 2.0m | 23% |
| 37 | Claude Haiku 5.5 (Adaptive) | 44.3% | $0.0018 | 19.3s | 18% |
| 38 | Claude Sonnet 4 | 53.0% | $0.032 | 43.7s | 22% |
| 39 | Claude Sonnet 4.6 | 53.3% | $0.031 | 39.3s | 21% |
| 40 | Mistral Medium 3.5 (Reasoning) | 46.1% | $0.018 | 18.0s | 20% |
| 41 | Aion 3.0 Mini | 48.7% | $0.0053 | 1.2m | 21% |
| 42 | Aion 3.5 Mini (Reasoning, High) | 58.5% | $0.011 | 2.4m | 25% |
| 43 | Mistral Medium 3.5 | 42.4% | $0.018 | 18.2s | 22% |
| 44 | Llama 3.1 70B | 44.4% | $0.0015 | 29.4s | 17% |
| 45 | Kimi K3 (Reasoning, Low) | 53.4% | $0.028 | 1.1m | 22% |
| 46 | Claude Opus 4.5 | 58.8% | $0.070 | 53.4s | 27% |
| 47 | GPT-6.1 Sol (Reasoning, Medium) | 54.7% | $0.031 | 1.6m | 25% |
| 48 | DeepSeek V4 Flash (Reasoning) | 41.5% | $0.0007 | 31.1s | 18% |
| 49 | Z.AI GLM 5.1 | 52.9% | $0.014 | 1.5m | 20% |
| 50 | GPT-6 Sol | 42.0% | $0.027 | 51.4s | 26% |
| 51 | DeepSeek V4 Flash | 42.5% | $0.0006 | 31.6s | 16% |
| 52 | Aion 3.0 | 48.6% | $0.024 | 1.0m | 21% |
| 53 | GPT-5.4 Mini (Reasoning) | 45.0% | $0.022 | 28.1s | 19% |
| 54 | Gemini 2.5 Flash Lite | 34.5% | $0.0009 | 9.5s | 18% |
| 55 | Grok 4.20 (Reasoning) | 45.7% | $0.018 | 1.5m | 25% |
| 56 | ByteDance Seed 1.6 Flash | 38.0% | $0.0013 | 27.3s | 18% |
| 57 | Claude Sonnet 5.5 (Reasoning) | 48.4% | $0.042 | 36.9s | 22% |
| 58 | Claude Opus 5 (Reasoning, Low) | 66.2% | $0.097 | 1.0m | 27% |
| 59 | MiniMax M2.7 | 46.3% | $0.0040 | 1.1m | 17% |
| 60 | Claude Opus 5.5 (Reasoning) | 60.9% | $0.092 | 56.0s | 28% |
| 61 | Claude Opus 5 (Reasoning) | 64.8% | $0.098 | 1.0m | 28% |
| 62 | GPT-4o, Aug. 6th (temp=1) | 44.8% | $0.018 | 24.4s | 17% |
| 63 | Ministral 8B | 37.6% | $0.0004 | 10.4s | 15% |
| 64 | Kimi K3 (Reasoning, High) | 54.0% | $0.044 | 1.8m | 27% |
| 65 | Gemini 3.8 Flash (Reasoning, Medium) | 41.0% | $0.014 | 18.0s | 17% |
| 66 | GPT-5.6 Luna | 35.0% | $0.015 | 15.8s | 20% |
| 67 | Xiaomi MIMO v2.5 Pro | 41.1% | $0.0085 | 53.5s | 19% |
| 68 | GPT-5.6 Luna (Reasoning, Medium) | 34.1% | $0.017 | 18.0s | 21% |
| 69 | GPT-4.1 | 39.4% | $0.018 | 44.7s | 21% |
| 70 | DeepSeek V3 (2025-03-24) | 42.0% | $0.0014 | 39.4s | 14% |
| 71 | Gemma 3 12B | 36.6% | $0.0004 | 41.3s | 17% |
| 72 | Ministral 3 8B | 38.5% | $0.0008 | 19.6s | 14% |
| 73 | Mistral Large 2 | 40.1% | $0.013 | 29.4s | 16% |
| 74 | Mistral Large 3 | 36.9% | $0.0033 | 30.3s | 16% |
| 75 | Claude Sonnet 5 | 46.7% | $0.027 | 33.5s | 16% |
| 76 | Claude Sonnet 5 (Reasoning, Low) | 49.8% | $0.031 | 38.4s | 15% |
| 77 | GPT-6 Sol (Reasoning, Medium) | 42.8% | $0.031 | 1.0m | 22% |
| 78 | GPT-6 Luna | 30.8% | $0.0013 | 32.6s | 19% |
| 79 | Gemini 3.5 Flash Lite (Reasoning) | 37.5% | $0.0035 | 6.6s | 12% |
| 80 | GPT-5.6 Terra (Reasoning, Medium) | 45.1% | $0.044 | 35.2s | 20% |
| 81 | Gemini 2.5 Flash Lite (Reasoning) | 33.3% | $0.0028 | 30.8s | 17% |
| 82 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 41.4% | $0.0035 | 6.3s | 9% |
| 83 | GPT-4o Mini (temp=1) | 38.9% | $0.0012 | 34.8s | 13% |
| 84 | Claude Sonnet 4.6 (Reasoning) | 53.7% | $0.060 | 1.2m | 22% |
| 85 | Gemma 3 27B | 39.8% | $0.0006 | 52.6s | 14% |
| 86 | Claude Opus 4.8 (Reasoning, Low) | 53.0% | $0.071 | 41.9s | 22% |
| 87 | Claude Opus 4.6 | 56.4% | $0.078 | 1.2m | 25% |
| 88 | Xiaomi MIMO v2.5 | 36.7% | $0.0054 | 31.8s | 15% |
| 89 | Claude Opus 4.8 (Reasoning) | 51.4% | $0.071 | 41.7s | 22% |
| 90 | Claude Opus 4.6 (Reasoning) | 58.5% | $0.088 | 1.4m | 26% |
| 91 | GPT-5.6 Terra | 42.7% | $0.046 | 36.9s | 21% |
| 92 | Qwen 3.6 Flash | 38.1% | $0.010 | 41.4s | 16% |
| 93 | GPT-4.1 Nano | 34.2% | $0.0007 | 13.3s | 12% |
| 94 | Qwen 3.6 35B | 37.5% | $0.0083 | 1.0m | 17% |
| 95 | Cohere Command R+ (Aug. 2024) | 45.9% | $0.020 | 52.5s | 13% |
| 96 | GPT-5.4 (Reasoning) | 65.0% | $0.089 | 2.6m | 29% |
| 97 | Mistral Large 4.0 | 39.7% | $0.0063 | 1.1m | 15% |
| 98 | Claude Opus 4.7 (Reasoning) | 52.7% | $0.076 | 32.0s | 20% |
| 99 | GPT-6 Luna (Reasoning, Medium) | 31.2% | $0.0016 | 43.0s | 16% |
| 100 | GPT-5.4 Nano | 28.8% | $0.0057 | 26.3s | 16% |
| 101 | GPT-6 Luna (Reasoning, High) | 29.9% | $0.0023 | 57.1s | 17% |
| 102 | Claude Sonnet 5 (Reasoning) | 44.5% | $0.030 | 38.9s | 13% |
| 103 | GPT-5.1 | 51.4% | $0.054 | 1.8m | 22% |
| 104 | Thinking Machines Inkling | 39.5% | $0.0075 | 1.5m | 16% |
| 105 | Gemini 2.5 Flash | 28.1% | $0.0052 | 10.6s | 13% |
| 106 | Gemini 3.7 Flash (Reasoning, Medium) | 36.5% | $0.012 | 18.2s | 10% |
| 107 | Muse Spark 1.2 (Reasoning, Medium) | 36.2% | $0.018 | 38.3s | 14% |
| 108 | Z.AI GLM 4.6 | 28.9% | $0.0065 | 51.5s | 17% |
| 109 | GPT-5.4 Nano (Reasoning, Low) | 26.5% | $0.0055 | 20.6s | 15% |
| 110 | DeepSeek V4 Pro (Reasoning) | 46.7% | $0.015 | 3.1m | 23% |
| 111 | Xiaomi MIMO v2.6 Flash | 37.2% | $0.0008 | 1.8m | 17% |
| 112 | Gemma 3 4B | 29.4% | $0.0002 | 20.0s | 11% |
| 113 | GPT-5.4 Nano (Reasoning) | 26.8% | $0.0061 | 24.5s | 15% |
| 114 | Mistral NeMO | 28.6% | $0.0005 | 10.1s | 10% |
| 115 | Qwen 3 32B | 32.1% | $0.0015 | 54.6s | 13% |
| 116 | WizardLM 2 8x22b | 38.5% | $0.0026 | 1.8m | 16% |
| 117 | Gemini 2.5 Flash (Reasoning) | 32.2% | $0.011 | 21.5s | 11% |
| 118 | DeepSeek V3.2 | 33.7% | $0.0014 | 1.9m | 17% |
| 119 | Muse Spark 1.3 (Reasoning, Medium) | 41.1% | $0.025 | 1.8m | 18% |
| 120 | Gemini 3.1 Flash Lite (Reasoning) | 23.5% | $0.0030 | 11.9s | 11% |
| 121 | Z.AI GLM 4.5 | 29.0% | $0.0051 | 42.1s | 12% |
| 122 | o4 Mini | 25.8% | $0.015 | 25.7s | 14% |
| 123 | Ministral 3B | 23.3% | $0.0001 | 8.1s | 10% |
| 124 | Gemini 3.5 Flash (Reasoning, Minimal) | 30.7% | $0.018 | 12.0s | 10% |
| 125 | Aion 2.0 | 28.8% | $0.0064 | 1.3m | 15% |
| 126 | GPT-4.1 Mini | 24.8% | $0.0027 | 19.0s | 10% |
| 127 | Kimi K2.5 | 43.7% | $0.019 | 3.2m | 22% |
| 128 | Z.AI GLM 4.5 Air | 28.2% | $0.0029 | 58.2s | 12% |
| 129 | Gemini 3.6 Flash (Reasoning, Minimal) | 26.2% | $0.017 | 14.3s | 11% |
| 130 | Gemini 2.5 Pro | 29.5% | $0.036 | 36.2s | 16% |
| 131 | GPT-5.6 Sol (Reasoning, Medium) | 49.7% | $0.108 | 1.2m | 25% |
| 132 | GPT-5.5 (Reasoning, Low) | 55.5% | $0.139 | 1.8m | 32% |
| 133 | Qwen 3.5 Plus (2026-02-15) | 22.7% | $0.0060 | 31.5s | 12% |
| 134 | DeepSeek V4 Flash 0731 (Reasoning, High) | 37.9% | $0.0022 | 2.6m | 15% |
| 135 | MiniMax M3 | 44.7% | $0.0060 | 3.1m | 16% |
| 136 | Gemini 3.1 Flash Lite (Preview) | 21.3% | $0.0030 | 8.4s | 8% |
| 137 | o4 Mini High | 28.1% | $0.025 | 47.2s | 14% |
| 138 | GPT-5.5 | 56.1% | $0.139 | 1.7m | 29% |
| 139 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 61.1% | $0.0031 | 6.5m | 26% |
| 140 | GPT-5.6 Sol | 47.0% | $0.105 | 1.2m | 22% |
| 141 | Gemini 3.6 Flash (Reasoning) | 33.4% | $0.044 | 32.5s | 11% |
| 142 | DeepSeek V3.1 | 26.6% | $0.0020 | 1.8m | 13% |
| 143 | Grok 4.3 | 21.7% | $0.0069 | 30.5s | 9% |
| 144 | DeepSeek V4 Pro 0813 (Reasoning, High) | 33.9% | $0.025 | 1.8m | 13% |
| 145 | Qwen 3.5 Plus (2026-04-20) | 31.8% | $0.017 | 1.8m | 12% |
| 146 | Ministral 3 3B | 18.7% | $0.0005 | 11.1s | 5% |
| 147 | DeepSeek V3 (2024-12-26) | 22.0% | $0.0021 | 54.6s | 7% |
| 148 | Gemini 3 Flash (Preview) | 17.4% | $0.0078 | 19.6s | 7% |
| 149 | DeepSeek-V2 Chat | 21.7% | $0.0021 | 53.3s | 6% |
| 150 | Qwen 3.5 397B A17B | 33.8% | $0.014 | 3.0m | 15% |
| 151 | Gemini 3.1 Flash Lite | 19.0% | $0.0030 | 12.1s | 3% |
| 152 | Muse Glimmer 30B (Reasoning, Medium) | 16.3% | $0.0038 | 43.4s | 7% |
| 153 | GPT-4o, Aug. 6th (temp=0) | 17.5% | $0.023 | 22.7s | 8% |
| 154 | GPT-5.5 (Reasoning, Medium) | 51.9% | $0.142 | 1.8m | 25% |
| 155 | Z.AI GLM 4.7 Flash | 16.8% | $0.0017 | 1.2m | 8% |
| 156 | Qwen 3.6 Max Preview | 44.1% | $0.050 | 3.5m | 19% |
| 157 | Thinking Machines Inkling Small (Reasoning, High) | 22.3% | $0.0088 | 1.7m | 9% |
| 158 | GPT-5 Mini | 17.7% | $0.0100 | 57.4s | 7% |
| 159 | Gemma 4 31B | 19.2% | $0.0010 | 1.6m | 8% |
| 160 | Gemini 3 Flash (Preview, Reasoning) | 17.3% | $0.012 | 30.1s | 5% |
| 161 | Gemini 3.5 Flash (Reasoning) | 30.0% | $0.071 | 37.6s | 11% |
| 162 | Gemma 4 26B | 14.2% | $0.0009 | 55.1s | 6% |
| 163 | Grok 4.6 (Reasoning, High) | 30.9% | $0.042 | 2.5m | 15% |
| 164 | Arcee AI: Trinity Mini | 11.6% | $0.0003 | 9.2s | 0% |
| 165 | Grok 4.7 (Reasoning, High) | 45.5% | $0.074 | 3.9m | 22% |
| 166 | Z.AI GLM 4.7 | 16.6% | $0.010 | 1.4m | 8% |
| 167 | Qwen 3.5 Flash | 12.9% | $0.0025 | 47.5s | 2% |
| 168 | Qwen 2.5 72B | 8.8% | $0.0010 | 36.7s | 2% |
| 169 | Nemotron 3 Super | 13.3% | $0.0000 | 1.4m | 5% |
| 170 | Thinking Machines Inkling (Reasoning) | 44.6% | $0.025 | 5.1m | 16% |
| 171 | Claude Opus 4 | 57.5% | $0.209 | 1.4m | 28% |
| 172 | Claude Haiku 5.5 (Reasoning, Max) | 61.1% | $0.049 | 7.5m | 28% |
| 173 | Mistral Large 4.0 (Reasoning) | 31.3% | $0.023 | 3.4m | 12% |
| 174 | Qwen 3.8 Flash (Reasoning) | 23.5% | $0.0064 | 3.1m | 10% |
| 175 | GPT-4o Mini (temp=0) | 9.5% | $0.0012 | 34.8s | 0% |
| 176 | ByteDance Seed 2.0 Lite | 22.0% | $0.012 | 2.2m | 6% |
| 177 | GPT-5.2 | 22.9% | $0.056 | 1.5m | 11% |
| 178 | GPT-5 Nano | 13.5% | $0.0042 | 1.4m | 2% |
| 179 | Inception Mercury 2 | 1.1% | $0.0032 | 7.0s | 0% |
| 180 | Z.AI GLM 5.3 (Reasoning, Max) | 64.7% | $0.066 | 7.3m | 25% |
| 181 | Gemma 4 31B (Reasoning) | 15.2% | $0.0014 | 2.2m | 5% |
| 182 | Qwen 3.6 27B | 22.7% | $0.025 | 2.3m | 6% |
| 183 | Hy4 Preview (Reasoning, High) | 35.6% | $0.040 | 4.4m | 16% |
| 184 | Qwen 3.5 35B | 14.4% | $0.018 | 1.0m | 1% |
| 185 | Gemma 4 26B (Reasoning) | 13.4% | $0.0013 | 2.0m | 3% |
| 186 | Nemotron 3 Nano | 7.5% | $0.0010 | 1.1m | 0% |
| 187 | GPT-5 | 29.2% | $0.065 | 2.8m | 13% |
| 188 | Qwen 3.5 9B | 7.6% | $0.0011 | 1.4m | 0% |
| 189 | Grok 4.3 (Reasoning) | 16.9% | $0.021 | 2.3m | 5% |
| 190 | Qwen 3.5 122B | 8.2% | $0.025 | 1.1m | 0% |
| 191 | ByteDance Seed 2.0 Mini | 22.7% | $0.0045 | 4.9m | 9% |
| 192 | Qwen 3.5 27B | 6.7% | $0.020 | 1.6m | 0% |
| 193 | GPT-OSS 120B | 0.9% | $0.0015 | 1.8m | 0% |
| 194 | ByteDance Seed 1.6 | 11.8% | $0.013 | 2.5m | 0% |
| 195 | Mistral Small 3.2 24B | 25.5% | $0.0069 | 5.7m | 9% |
| 196 | Gemini 3.1 Pro (Preview) | 23.9% | $0.107 | 1.8m | 6% |
| 197 | Qwen 3.7 Max | 17.6% | $0.068 | 2.3m | 1% |
| 198 | Kimi K2.6 | 35.9% | $0.058 | 6.5m | 16% |
| 199 | Qwen 3.8 27B (Reasoning, XHigh) | 17.6% | $0.040 | 4.7m | 5% |
| 200 | Qwen 3.8 Max (Reasoning, XHigh) | 31.4% | $0.083 | 5.9m | 16% |
| 38.67% | |||||