Language
9 scenarios across 2 subcategories. 146 models scored.
Subcategories
| Subcategory | Avg Score | Best Model | Best Score |
|---|---|---|---|
| Comprehension | 85.10% | GPT-5.6 Sol (Reasoning) | 100.00% |
| Generation | 89.14% | Qwen3.6 Max Preview | 100.00% |
Model Leaderboard
All models ranked by their Language category score.
| # | Model | Language | Comprehension | Generation | Overall |
|---|---|---|---|---|---|
| 1 | Qwen3.6 Max Preview | 100.00% | 100.00% | 100.00% | 93.72% |
| 2 | Claude Sonnet 4.6 | 100.00% | 100.00% | 100.00% | 90.66% |
| 3 | DeepSeek-V2 Chat | 100.00% | 100.00% | 100.00% | 84.09% |
| 4 | GPT-5.6 Sol (Reasoning) | 99.93% | 100.00% | 99.86% | 95.15% |
| 5 | Z.AI GLM 5 Turbo | 99.90% | 100.00% | 99.80% | 93.29% |
| 6 | Grok 4.5 (Reasoning, High) | 99.82% | 100.00% | 99.64% | 94.12% |
| 7 | Z.AI GLM 5.2 (Reasoning, High) | 99.82% | 100.00% | 99.64% | 93.41% |
| 8 | GPT-5.5 (Reasoning) | 99.69% | 100.00% | 99.37% | 93.72% |
| 9 | Claude Opus 4.5 | 99.66% | 100.00% | 99.31% | 89.60% |
| 10 | Hermes 3 405B | 99.57% | 100.00% | 99.14% | 80.80% |
| 11 | GPT-5.6 Luna | 99.33% | 100.00% | 98.66% | 85.06% |
| 12 | GPT-5.5 (Reasoning, Low) | 99.24% | 100.00% | 98.49% | 92.51% |
| 13 | Claude Sonnet 5 (Reasoning) | 99.04% | 100.00% | 98.08% | 90.40% |
| 14 | Claude Opus 4.7 (Reasoning) | 98.77% | 100.00% | 97.53% | 92.53% |
| 15 | GPT-5.4 Mini (Reasoning) | 98.12% | 100.00% | 96.25% | 89.82% |
| 16 | Claude Sonnet 5 (Reasoning, Low) | 98.06% | 100.00% | 96.12% | 90.16% |
| 17 | Claude Sonnet 4.6 (Reasoning) | 97.58% | 100.00% | 95.15% | 93.64% |
| 18 | Grok 4.3 (Reasoning) | 97.50% | 95.00% | 100.00% | 90.99% |
| 19 | Gemini 3.5 Flash (Reasoning, Minimal) | 97.50% | 95.00% | 100.00% | 85.88% |
| 20 | Z.AI GLM 4.5 | 97.33% | 95.00% | 99.67% | 84.95% |
| 21 | GPT-5.6 Terra (Reasoning) | 97.22% | 95.00% | 99.44% | 92.49% |
| 22 | GPT-OSS 120B | 97.18% | 95.00% | 99.36% | 84.81% |
| 23 | Qwen 3.5 Plus (2026-04-20) | 97.14% | 100.00% | 94.29% | 89.79% |
| 24 | MoonshotAI: Kimi K2.5 | 97.10% | 100.00% | 94.19% | 90.86% |
| 25 | Qwen3.7 Max | 97.05% | 100.00% | 94.10% | 94.55% |
| 26 | DeepSeek V3.1 | 96.87% | 95.00% | 98.74% | 82.35% |
| 27 | ByteDance Seed 2.0 Lite | 96.80% | 100.00% | 93.60% | 84.27% |
| 28 | MoonshotAI: Kimi K2.6 | 96.77% | 100.00% | 93.53% | 92.57% |
| 29 | Gemini 3.1 Flash Lite (Reasoning) | 96.70% | 95.00% | 98.40% | 85.91% |
| 30 | GPT-5.6 Luna (Reasoning) | 96.67% | 95.00% | 98.34% | 90.61% |
| 31 | Grok 4.20 (Reasoning) | 96.61% | 95.00% | 98.22% | 90.87% |
| 32 | Z.AI GLM 4.6 | 96.60% | 100.00% | 93.20% | 87.64% |
| 33 | GPT-5 Mini | 96.49% | 95.00% | 97.98% | 91.31% |
| 34 | Claude Opus 4.8 (Reasoning) | 96.38% | 95.00% | 97.76% | 92.33% |
| 35 | Claude Opus 4.8 (Reasoning, Low) | 96.31% | 95.00% | 97.63% | 91.89% |
| 36 | Aion 2.0 | 96.17% | 100.00% | 92.34% | 86.66% |
| 37 | Claude Opus 4.6 | 96.13% | 100.00% | 92.27% | 92.31% |
| 38 | Claude Opus 4.6 (Reasoning) | 96.12% | 100.00% | 92.23% | 95.06% |
| 39 | MiniMax M2.5 | 96.05% | 95.00% | 97.10% | 86.71% |
| 40 | ByteDance Seed 1.6 | 95.63% | 100.00% | 91.26% | 89.59% |
| 41 | Qwen 3.5 27B | 95.52% | 100.00% | 91.05% | 90.05% |
| 42 | Claude Sonnet 5 | 95.50% | 95.00% | 96.00% | 87.34% |
| 43 | Gemma 4 26B (Reasoning) | 95.20% | 95.00% | 95.40% | 89.02% |
| 44 | Qwen 3.5 Plus (2026-02-15) | 95.10% | 100.00% | 90.21% | 86.17% |
| 45 | Z.AI GLM 4.5 Air | 95.05% | 95.00% | 95.10% | 80.74% |
| 46 | Qwen 3.5 122B | 95.01% | 100.00% | 90.03% | 90.32% |
| 47 | Qwen 3.5 397B A17B | 95.01% | 100.00% | 90.03% | 91.09% |
| 48 | Gemini 3 Flash (Preview) | 95.00% | 90.00% | 100.00% | 85.47% |
| 49 | Gemini 3.1 Flash Lite (Preview) | 94.98% | 95.00% | 94.95% | 85.41% |
| 50 | Gemini 3 Flash (Preview, Reasoning) | 94.93% | 95.00% | 94.87% | 89.93% |
| 51 | GPT-5.4 (Reasoning) | 94.90% | 95.00% | 94.80% | 93.85% |
| 52 | Gemini 3.1 Pro (Preview) | 94.90% | 95.00% | 94.80% | 94.08% |
| 53 | DeepSeek V4 Flash (Reasoning) | 94.76% | 100.00% | 89.51% | 88.06% |
| 54 | MiniMax M3 | 94.71% | 100.00% | 89.43% | 90.45% |
| 55 | GPT-5.6 Sol | 94.60% | 90.00% | 99.20% | 90.76% |
| 56 | Grok 4.5 (Reasoning, Low) | 94.50% | 95.00% | 94.00% | 90.94% |
| 57 | Gemini 3.5 Flash (Reasoning) | 94.41% | 95.00% | 93.83% | 93.35% |
| 58 | GPT-5.5 | 94.15% | 90.00% | 98.29% | 89.37% |
| 59 | GPT-4.1 | 93.91% | 90.00% | 97.82% | 86.82% |
| 60 | Aion 3.0 Mini | 93.68% | 90.00% | 97.35% | 83.69% |
| 61 | GPT-5.1 | 93.64% | 90.00% | 97.28% | 90.73% |
| 62 | Qwen 3.6 35B | 93.56% | 90.00% | 97.12% | 87.66% |
| 63 | Claude Opus 4 | 93.01% | 100.00% | 86.02% | 87.22% |
| 64 | Gemini 2.5 Pro | 92.57% | 90.00% | 95.14% | 88.44% |
| 65 | GPT-5.4 Mini (Reasoning, Low) | 92.45% | 85.00% | 99.89% | 83.57% |
| 66 | Claude Sonnet 4.5 | 92.39% | 95.00% | 89.77% | 87.54% |
| 67 | Claude Opus 4.7 | 92.32% | 85.00% | 99.65% | 89.90% |
| 68 | Z.AI GLM 5 | 92.06% | 95.00% | 89.12% | 89.60% |
| 69 | Mistral Large 3 | 92.02% | 100.00% | 84.05% | 84.29% |
| 70 | Gemma 4 26B | 92.02% | 90.00% | 94.03% | 84.89% |
| 71 | Qwen 3.5 35B | 91.95% | 100.00% | 83.90% | 87.01% |
| 72 | Qwen 3.5 Flash | 91.94% | 95.00% | 88.89% | 85.66% |
| 73 | GPT-5.6 Terra | 91.87% | 85.00% | 98.75% | 88.23% |
| 74 | Claude Haiku 4.5 | 91.84% | 95.00% | 88.67% | 83.36% |
| 75 | Z.AI GLM 5.1 | 91.57% | 85.00% | 98.14% | 93.74% |
| 76 | GPT-5 | 91.50% | 85.00% | 98.01% | 91.48% |
| 77 | Claude Sonnet 4 | 91.31% | 90.00% | 92.61% | 87.64% |
| 78 | GPT-5.2 | 91.19% | 85.00% | 97.39% | 89.45% |
| 79 | Gemini 3.1 Flash Lite | 90.90% | 85.00% | 96.80% | 85.09% |
| 80 | GPT-5.4 (Reasoning, Low) | 90.79% | 85.00% | 96.58% | 90.91% |
| 81 | ByteDance Seed 2.0 Mini | 90.12% | 90.00% | 90.24% | 85.69% |
| 82 | GPT-4.1 Mini | 89.64% | 80.00% | 99.27% | 81.40% |
| 83 | Qwen 3.6 Flash | 89.33% | 85.00% | 93.66% | 89.31% |
| 84 | Qwen 3.6 27B | 89.01% | 90.00% | 88.01% | 88.33% |
| 85 | GPT-5.4 Mini | 88.75% | 80.00% | 97.50% | 80.45% |
| 86 | DeepSeek V4 Pro (Reasoning) | 88.51% | 85.00% | 92.02% | 89.28% |
| 87 | DeepSeek V4 Flash | 88.50% | 90.00% | 87.00% | 82.02% |
| 88 | Qwen 3.5 9B | 88.18% | 90.00% | 86.36% | 84.05% |
| 89 | DeepSeek V3 (2024-12-26) | 87.88% | 100.00% | 75.76% | 82.62% |
| 90 | Xiaomi MIMO v2.5 Pro | 87.69% | 85.00% | 90.37% | 86.05% |
| 91 | Z.AI GLM 4.7 Flash | 87.67% | 95.00% | 80.35% | 82.21% |
| 92 | Nemotron 3 Nano | 87.63% | 80.00% | 95.26% | 74.50% |
| 93 | Inception Mercury 2 | 87.32% | 75.00% | 99.64% | 81.99% |
| 94 | Aion 3.0 | 86.85% | 80.00% | 93.70% | 88.78% |
| 95 | DeepSeek V3 (2025-03-24) | 86.42% | 100.00% | 72.83% | 79.93% |
| 96 | Gemini 2.5 Flash | 86.23% | 75.00% | 97.46% | 80.61% |
| 97 | Gemini 2.5 Flash (Reasoning) | 86.06% | 75.00% | 97.13% | 84.14% |
| 98 | Z.AI GLM 4.7 | 85.46% | 80.00% | 90.93% | 87.67% |
| 99 | Mistral Large 2 | 85.22% | 100.00% | 70.43% | 81.50% |
| 100 | DeepSeek V3.2 | 85.01% | 80.00% | 90.03% | 82.22% |
| 101 | MiniMax M2.7 | 84.80% | 100.00% | 69.59% | 86.23% |
| 102 | Grok 4.3 | 84.74% | 75.00% | 94.47% | 78.00% |
| 103 | Qwen 3 32B | 84.61% | 90.00% | 79.21% | 79.37% |
| 104 | GPT-5.4 Nano (Reasoning) | 83.99% | 70.00% | 97.99% | 80.02% |
| 105 | Gemma 4 31B (Reasoning) | 83.82% | 75.00% | 92.64% | 89.64% |
| 106 | Gemini 2.5 Flash Lite | 82.75% | 80.00% | 85.50% | 79.91% |
| 107 | GPT-4o, Aug. 6th (temp=1) | 82.21% | 65.00% | 99.43% | 81.28% |
| 108 | GPT-5.4 Nano (Reasoning, Low) | 81.87% | 70.00% | 93.74% | 77.46% |
| 109 | Hermes 3 70B | 81.66% | 75.00% | 88.33% | 69.74% |
| 110 | GPT-5.4 | 81.49% | 65.00% | 97.98% | 84.31% |
| 111 | Nemotron 3 Super | 81.41% | 65.00% | 97.82% | 81.69% |
| 112 | GPT-5.4 Nano | 80.82% | 70.00% | 91.64% | 72.16% |
| 113 | Mistral NeMO | 80.80% | 95.00% | 66.60% | 63.80% |
| 114 | Llama 3.1 70B | 80.18% | 75.00% | 85.36% | 77.41% |
| 115 | Gemma 3 12B | 80.10% | 70.00% | 90.19% | 76.07% |
| 116 | o4 Mini | 80.00% | 60.00% | 100.00% | 86.56% |
| 117 | o4 Mini High | 79.76% | 60.00% | 99.51% | 88.78% |
| 118 | GPT-4.1 Nano | 78.95% | 65.00% | 92.91% | 69.90% |
| 119 | Grok 4.20 | 78.86% | 65.00% | 92.72% | 81.21% |
| 120 | WizardLM 2 8x22b | 78.05% | 95.00% | 61.10% | 71.45% |
| 121 | GPT-4o Mini (temp=1) | 77.50% | 55.00% | 100.00% | 77.82% |
| 122 | Gemma 3 27B | 77.21% | 65.00% | 89.42% | 75.70% |
| 123 | GPT-5 Nano | 77.18% | 55.00% | 99.35% | 80.16% |
| 124 | Xiaomi MIMO v2.5 | 76.33% | 65.00% | 87.66% | 83.95% |
| 125 | Gemma 4 31B | 75.00% | 50.00% | 100.00% | 85.23% |
| 126 | GPT-4o, Aug. 6th (temp=0) | 75.00% | 50.00% | 100.00% | 82.18% |
| 127 | GPT-4o Mini (temp=0) | 75.00% | 50.00% | 100.00% | 76.86% |
| 128 | Gemini 2.5 Flash Lite (Reasoning) | 74.36% | 65.00% | 83.71% | 83.10% |
| 129 | DeepSeek V4 Pro | 72.80% | 70.00% | 75.59% | 82.05% |
| 130 | Mistral Small 3.2 24B | 72.77% | 75.00% | 70.53% | 77.36% |
| 131 | Cydonia 24B V4.1 | 72.49% | 95.00% | 49.98% | 72.68% |
| 132 | Gemma 3 4B | 72.28% | 70.00% | 74.56% | 66.33% |
| 133 | Arcee AI: Trinity Mini | 70.59% | 60.00% | 81.18% | 67.68% |
| 134 | Qwen 2.5 72B | 68.95% | 70.00% | 67.91% | 73.17% |
| 135 | Ministral 3 3B | 68.10% | 100.00% | 36.20% | 65.02% |
| 136 | Cohere Command R+ (Aug. 2024) | 66.58% | 60.00% | 73.15% | 67.04% |
| 137 | ByteDance Seed 1.6 Flash | 61.23% | 40.00% | 82.45% | 70.92% |
| 138 | Qwen3 235B A22B Instruct 2507 | 60.83% | 75.00% | 46.67% | 78.07% |
| 139 | Mistral Small 4 (Reasoning) | 60.53% | 50.00% | 71.06% | 79.48% |
| 140 | Writer: Palmyra X5 | 56.58% | 70.00% | 43.16% | 78.11% |
| 141 | Ministral 8B | 53.91% | 55.00% | 52.81% | 63.77% |
| 142 | Mistral Small 4 | 51.96% | 55.00% | 48.93% | 75.23% |
| 143 | Mistral Medium 3.1 | 49.50% | 50.00% | 49.00% | 76.08% |
| 144 | Ministral 3 8B | 48.96% | 50.00% | 47.92% | 69.98% |
| 145 | Ministral 3B | 42.25% | 25.00% | 59.49% | 59.25% |
| 146 | Ministral 3 14B | 30.00% | 50.00% | 10.00% | 70.45% |