Generation
Subcategory of Language. 155 models scored.
Model Leaderboard
All models ranked by their Generation subcategory score.
| # | Model | Generation | Language | Overall |
|---|---|---|---|---|
| 1 | Qwen3.6 Max Preview | 100.00% | 100.00% | 94.54% |
| 2 | Grok 4.3 (Reasoning) | 100.00% | 97.50% | 93.60% |
| 3 | Claude Sonnet 4.6 | 100.00% | 100.00% | 91.15% |
| 4 | o4 Mini | 100.00% | 80.00% | 88.35% |
| 5 | Gemma 4 31B | 100.00% | 75.00% | 86.91% |
| 6 | Gemini 3.5 Flash (Reasoning, Minimal) | 100.00% | 97.50% | 86.47% |
| 7 | Gemini 3 Flash (Preview) | 100.00% | 95.00% | 85.35% |
| 8 | DeepSeek-V2 Chat | 100.00% | 100.00% | 84.83% |
| 9 | Stealth: Aurora Alpha | 100.00% | 92.50% | 83.79% |
| 10 | GPT-4o, Aug. 6th (temp=0) | 100.00% | 75.00% | 82.45% |
| 11 | GPT-4o Mini (temp=1) | 100.00% | 77.50% | 79.08% |
| 12 | GPT-4o Mini (temp=0) | 100.00% | 75.00% | 78.29% |
| 13 | GPT-5.4 Mini (Reasoning, Low) | 99.89% | 92.45% | 85.75% |
| 14 | Z.AI GLM 5 Turbo | 99.80% | 99.90% | 94.27% |
| 15 | Z.AI GLM 4.5 | 99.67% | 97.33% | 86.27% |
| 16 | Claude Opus 4.7 | 99.65% | 92.32% | 89.93% |
| 17 | Inception Mercury 2 | 99.64% | 87.32% | 83.85% |
| 18 | o4 Mini High | 99.51% | 79.76% | 90.29% |
| 19 | GPT-4o, Aug. 6th (temp=1) | 99.43% | 82.21% | 82.62% |
| 20 | GPT-5.5 (Reasoning) | 99.37% | 99.69% | 92.98% |
| 21 | GPT-OSS 120B | 99.36% | 97.18% | 86.44% |
| 22 | GPT-5 Nano | 99.35% | 77.18% | 82.60% |
| 23 | Claude Opus 4.5 | 99.31% | 99.66% | 89.69% |
| 24 | GPT-4.1 Mini | 99.27% | 89.64% | 83.20% |
| 25 | Hermes 3 405B | 99.14% | 99.57% | 82.86% |
| 26 | DeepSeek V3.1 | 98.74% | 96.87% | 82.39% |
| 27 | GPT-5.5 (Reasoning, Low) | 98.49% | 99.24% | 92.59% |
| 28 | Gemini 3.1 Flash Lite (Reasoning) | 98.40% | 96.70% | 86.41% |
| 29 | GPT-5.5 | 98.29% | 94.15% | 89.09% |
| 30 | Grok 4.20 (Reasoning) | 98.22% | 96.61% | 91.39% |
| 31 | Grok 4.20 (Beta, Reasoning) | 98.15% | 99.08% | 91.49% |
| 32 | Z.AI GLM 5.1 | 98.14% | 91.57% | 94.37% |
| 33 | GPT-5 | 98.01% | 91.50% | 91.93% |
| 34 | GPT-5.4 Nano (Reasoning) | 97.99% | 83.99% | 81.36% |
| 35 | GPT-5.4 | 97.98% | 81.49% | 84.32% |
| 36 | GPT-5 Mini | 97.98% | 96.49% | 92.62% |
| 37 | GPT-4.1 | 97.82% | 93.91% | 88.68% |
| 38 | Nemotron 3 Super | 97.82% | 81.41% | 84.56% |
| 39 | Claude Opus 4.8 (Reasoning) | 97.76% | 96.38% | 92.22% |
| 40 | Claude Opus 4.8 (Reasoning, Low) | 97.63% | 96.31% | 92.14% |
| 41 | Claude Opus 4.7 (Reasoning) | 97.53% | 98.77% | 93.23% |
| 42 | GPT-5.4 Mini | 97.50% | 88.75% | 82.43% |
| 43 | Gemini 2.5 Flash | 97.46% | 86.23% | 80.60% |
| 44 | GPT-4o, May 13th (temp=0) | 97.44% | 98.72% | 85.36% |
| 45 | GPT-5.2 | 97.39% | 91.19% | 90.26% |
| 46 | Grok 4.20 (Beta) | 97.34% | 91.17% | 83.85% |
| 47 | GPT-5.1 | 97.28% | 93.64% | 92.54% |
| 48 | Gemini 2.5 Flash (Reasoning) | 97.13% | 86.06% | 86.51% |
| 49 | Qwen 3.6 35B | 97.12% | 93.56% | 89.05% |
| 50 | MiniMax M2.5 | 97.10% | 96.05% | 88.71% |
| 51 | Gemini 3.1 Flash Lite | 96.80% | 90.90% | 85.75% |
| 52 | GPT-5.4 (Reasoning, Low) | 96.58% | 90.79% | 91.41% |
| 53 | GPT-5.4 Mini (Reasoning) | 96.25% | 98.12% | 90.65% |
| 54 | Claude 3.5 Sonnet | 96.24% | 85.62% | 84.24% |
| 55 | Grok 4 | 96.22% | 90.61% | 88.12% |
| 56 | Claude 3.7 Sonnet | 95.89% | 92.95% | 83.39% |
| 57 | Inception Mercury | 95.74% | 80.37% | 79.50% |
| 58 | Gemma 4 26B (Reasoning) | 95.40% | 95.20% | 91.49% |
| 59 | Nemotron 3 Nano | 95.26% | 87.63% | 77.73% |
| 60 | Claude Sonnet 4.6 (Reasoning) | 95.15% | 97.58% | 93.66% |
| 61 | Gemini 2.5 Pro | 95.14% | 92.57% | 88.53% |
| 62 | Z.AI GLM 4.5 Air | 95.10% | 95.05% | 83.12% |
| 63 | Gemini 3.1 Flash Lite (Preview) | 94.95% | 94.98% | 85.87% |
| 64 | Gemini 3 Flash (Preview, Reasoning) | 94.87% | 94.93% | 90.50% |
| 65 | GPT-5.4 (Reasoning) | 94.80% | 94.90% | 93.24% |
| 66 | Gemini 3.1 Pro (Preview) | 94.80% | 94.90% | 94.37% |
| 67 | Grok 4.3 | 94.47% | 84.74% | 78.66% |
| 68 | Qwen 3.5 Plus (2026-04-20) | 94.29% | 97.14% | 91.51% |
| 69 | MoonshotAI: Kimi K2.5 | 94.19% | 97.10% | 91.04% |
| 70 | Qwen3.7 Max | 94.10% | 97.05% | 95.75% |
| 71 | Gemma 4 26B | 94.03% | 92.02% | 85.84% |
| 72 | Gemini 3.5 Flash (Reasoning) | 93.83% | 94.41% | 94.08% |
| 73 | GPT-5.4 Nano (Reasoning, Low) | 93.74% | 81.87% | 79.48% |
| 74 | Qwen 3.6 Flash | 93.66% | 89.33% | 90.65% |
| 75 | ByteDance Seed 2.0 Lite | 93.60% | 96.80% | 84.80% |
| 76 | MoonshotAI: Kimi K2.6 | 93.53% | 96.77% | 92.31% |
| 77 | Z.AI GLM 4.6 | 93.20% | 96.60% | 89.11% |
| 78 | GPT-4.1 Nano | 92.91% | 78.95% | 71.94% |
| 79 | Grok 4.20 | 92.72% | 78.86% | 81.70% |
| 80 | Gemma 4 31B (Reasoning) | 92.64% | 83.82% | 91.71% |
| 81 | Claude Sonnet 4 | 92.61% | 91.31% | 88.72% |
| 82 | Aion 2.0 | 92.34% | 96.17% | 89.21% |
| 83 | Claude Opus 4.6 | 92.27% | 96.13% | 92.35% |
| 84 | Claude Opus 4.6 (Reasoning) | 92.23% | 96.12% | 95.02% |
| 85 | DeepSeek V4 Pro (Reasoning) | 92.02% | 88.51% | 90.10% |
| 86 | Stealth: Hunter Alpha | 91.70% | 93.35% | 87.34% |
| 87 | GPT-5.4 Nano | 91.64% | 80.82% | 74.40% |
| 88 | ByteDance Seed 1.6 | 91.26% | 95.63% | 90.70% |
| 89 | Qwen 3.5 27B | 91.05% | 95.53% | 90.85% |
| 90 | Z.AI GLM 4.7 | 90.93% | 85.46% | 88.69% |
| 91 | Xiaomi MIMO v2.5 Pro | 90.37% | 87.69% | 87.36% |
| 92 | ByteDance Seed 2.0 Mini | 90.24% | 90.12% | 86.91% |
| 93 | Qwen 3.5 Plus (2026-02-15) | 90.21% | 95.10% | 85.96% |
| 94 | Gemma 3 12B | 90.19% | 80.10% | 78.41% |
| 95 | GPT-4o, May 13th (temp=1) | 90.04% | 92.52% | 83.80% |
| 96 | Qwen 3.5 122B | 90.03% | 95.01% | 91.53% |
| 97 | Qwen 3.5 397B A17B | 90.03% | 95.01% | 91.73% |
| 98 | DeepSeek V3.2 | 90.03% | 85.01% | 82.25% |
| 99 | Claude Sonnet 4.5 | 89.77% | 92.39% | 88.03% |
| 100 | DeepSeek V4 Flash (Reasoning) | 89.51% | 94.76% | 89.01% |
| 101 | MiniMax M3 | 89.43% | 94.71% | 90.88% |
| 102 | Gemma 3 27B | 89.42% | 77.21% | 77.85% |
| 103 | Z.AI GLM 5 | 89.12% | 92.06% | 91.23% |
| 104 | Qwen 3.5 Flash | 88.89% | 91.94% | 86.38% |
| 105 | Claude Haiku 4.5 | 88.67% | 91.84% | 85.14% |
| 106 | Hermes 3 70B | 88.33% | 81.66% | 72.57% |
| 107 | Qwen 3.6 27B | 88.01% | 89.01% | 89.72% |
| 108 | Xiaomi MIMO v2.5 | 87.66% | 76.33% | 85.05% |
| 109 | Grok 4.1 Fast | 87.51% | 88.76% | 89.55% |
| 110 | Mistral Large | 87.27% | 88.64% | 80.15% |
| 111 | DeepSeek V4 Flash | 87.00% | 88.50% | 82.02% |
| 112 | Stealth: Healer Alpha | 86.90% | 88.45% | 85.93% |
| 113 | Qwen 3.5 9B | 86.36% | 88.18% | 86.05% |
| 114 | Claude Opus 4 | 86.02% | 93.01% | 87.69% |
| 115 | Gemini 2.5 Flash Lite | 85.50% | 82.75% | 81.08% |
| 116 | Llama 3.1 70B | 85.36% | 80.18% | 78.40% |
| 117 | Gemini 3 Pro (Preview) | 84.29% | 89.64% | 88.79% |
| 118 | Grok 4 Fast | 84.22% | 84.61% | 86.15% |
| 119 | Mistral Large 3 | 84.05% | 92.02% | 85.43% |
| 120 | Qwen 3.5 35B | 83.90% | 91.95% | 88.00% |
| 121 | Gemini 2.5 Flash Lite (Reasoning) | 83.71% | 74.36% | 85.75% |
| 122 | ByteDance Seed 1.6 Flash | 82.45% | 61.23% | 73.27% |
| 123 | Arcee AI: Trinity Mini | 81.18% | 70.59% | 70.90% |
| 124 | Claude 3 Haiku | 80.53% | 72.76% | 71.19% |
| 125 | Z.AI GLM 4.7 Flash | 80.35% | 87.67% | 84.82% |
| 126 | Qwen 3 32B | 79.21% | 84.61% | 82.21% |
| 127 | Arcee AI: Trinity Large (Preview) | 76.76% | 78.38% | 73.33% |
| 128 | DeepSeek V3 (2024-12-26) | 75.76% | 87.88% | 83.68% |
| 129 | DeepSeek V4 Pro | 75.59% | 72.80% | 82.63% |
| 130 | Gemma 3 4B | 74.56% | 72.28% | 68.57% |
| 131 | Cohere Command R+ (Aug. 2024) | 73.15% | 66.58% | 69.03% |
| 132 | Llama 3.1 8B | 73.13% | 64.06% | 63.35% |
| 133 | DeepSeek V3 (2025-03-24) | 72.83% | 86.42% | 81.99% |
| 134 | Mistral Small 4 (Reasoning) | 71.06% | 60.53% | 82.39% |
| 135 | Mistral Small 3.2 24B | 70.53% | 72.77% | 78.58% |
| 136 | Mistral Large 2 | 70.43% | 85.22% | 82.41% |
| 137 | MiniMax M2.7 | 69.59% | 84.80% | 89.10% |
| 138 | Qwen 2.5 72B | 67.91% | 68.95% | 75.46% |
| 139 | Skyfall 36B V2 | 67.88% | 73.94% | 65.76% |
| 140 | Mistral NeMO | 66.60% | 80.80% | 65.04% |
| 141 | LFM2 24B | 64.28% | 64.64% | 58.77% |
| 142 | WizardLM 2 8x22b | 61.10% | 78.05% | 71.06% |
| 143 | Ministral 3B | 59.49% | 42.25% | 61.29% |
| 144 | Ministral 8B | 52.81% | 53.91% | 64.87% |
| 145 | Rocinante 12B | 51.90% | 63.45% | 54.54% |
| 146 | Cydonia 24B V4.1 | 49.98% | 72.49% | 75.09% |
| 147 | Mistral Medium 3.1 | 49.00% | 49.50% | 77.83% |
| 148 | Mistral Small 4 | 48.93% | 51.96% | 76.46% |
| 149 | Ministral 3 8B | 47.92% | 48.96% | 71.76% |
| 150 | Qwen3 235B A22B Instruct 2507 | 46.67% | 60.83% | 80.10% |
| 151 | Writer: Palmyra X5 | 43.16% | 56.58% | 79.57% |
| 152 | Ministral 3 3B | 36.20% | 68.10% | 67.22% |
| 153 | Mistral Small Creative | 33.69% | 41.85% | 73.27% |
| 154 | Llama 3.1 Nemotron 70B | 33.61% | 46.80% | 74.70% |
| 155 | Ministral 3 14B | 10.00% | 30.00% | 72.54% |