Text Editing
18 scenarios across 3 subcategories. 202 models scored.
Subcategories
| Subcategory | Avg Score | Best Model | Best Score |
|---|---|---|---|
| Transformation | 87.97% | Grok 4.6 (Reasoning, High) | 98.49% |
| Preservation | 95.57% | Claude Opus 4.8 (Reasoning) | 100.00% |
| Structural Integrity | 98.97% | Claude Opus 5.5 (Reasoning) | 100.00% |
Model Leaderboard
All models ranked by their Text Editing category score.
| # | Model | Text Editing | Transformation | Preservation | Structural Integrity | Overall |
|---|---|---|---|---|---|---|
| 1 | Grok 4.6 (Reasoning, High) | 99.17% | 98.49% | 99.03% | 100.00% | 92.76% |
| 2 | Claude Sonnet 4 | 99.13% | 97.70% | 99.69% | 100.00% | 87.64% |
| 3 | Gemini 3.6 Flash (Reasoning) | 99.04% | 98.00% | 99.11% | 100.00% | 94.90% |
| 4 | Claude Sonnet 4.5 | 99.02% | 97.74% | 99.31% | 100.00% | 87.54% |
| 5 | Gemini 3.7 Flash (Reasoning, Medium) | 98.90% | 97.60% | 99.11% | 100.00% | 94.85% |
| 6 | Z.AI GLM 5.2 (Reasoning, High) | 98.90% | 98.00% | 98.70% | 100.00% | 93.41% |
| 7 | Z.AI GLM 5.1 | 98.90% | 97.82% | 98.88% | 100.00% | 93.74% |
| 8 | GPT-5 | 98.90% | 98.11% | 98.57% | 100.00% | 91.48% |
| 9 | Claude Opus 4.6 (Reasoning) | 98.86% | 97.85% | 98.72% | 100.00% | 95.06% |
| 10 | Gemini 3.8 Flash (Reasoning, Medium) | 98.84% | 97.41% | 99.11% | 100.00% | 95.72% |
| 11 | Grok 4.20 (Reasoning) | 98.83% | 97.60% | 98.90% | 100.00% | 90.87% |
| 12 | Gemma 4 31B (Reasoning) | 98.83% | 97.51% | 98.98% | 100.00% | 89.64% |
| 13 | GPT-5.5 (Reasoning, Medium) | 98.79% | 97.78% | 98.57% | 100.00% | 93.72% |
| 14 | Claude Opus 4.8 (Reasoning) | 98.78% | 96.33% | 100.00% | 100.00% | 92.33% |
| 15 | Z.AI GLM 5.3 (Reasoning, Max) | 98.75% | 97.36% | 98.90% | 100.00% | 95.20% |
| 16 | Grok 4.5 (Reasoning, High) | 98.73% | 97.10% | 99.08% | 100.00% | 94.12% |
| 17 | Muse Spark 1.1 (Reasoning, Medium) | 98.72% | 97.14% | 99.03% | 100.00% | 93.81% |
| 18 | Claude Opus 4.8 (Reasoning, Low) | 98.71% | 96.27% | 99.87% | 100.00% | 91.89% |
| 19 | Muse Wonder (Reasoning, Medium) | 98.71% | 97.07% | 99.06% | 100.00% | 95.47% |
| 20 | Qwen 3.5 27B | 98.69% | 97.53% | 98.55% | 100.00% | 90.05% |
| 21 | Hy4 Preview (Reasoning, High) | 98.60% | 96.87% | 98.93% | 100.00% | 94.80% |
| 22 | Claude Opus 5.5 (Reasoning) | 98.60% | 96.86% | 98.93% | 100.00% | 96.43% |
| 23 | Z.AI GLM 5 | 98.59% | 97.15% | 98.62% | 100.00% | 89.60% |
| 24 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 98.59% | 96.68% | 99.08% | 100.00% | 94.28% |
| 25 | GPT-5.5 (Reasoning, Low) | 98.59% | 96.83% | 98.93% | 100.00% | 92.51% |
| 26 | Qwen 3.6 Max Preview | 98.58% | 96.97% | 98.78% | 100.00% | 93.72% |
| 27 | Gemini 2.5 Pro | 98.58% | 96.93% | 98.80% | 100.00% | 88.44% |
| 28 | DeepSeek V4 Pro (Reasoning) | 98.56% | 97.09% | 98.60% | 100.00% | 89.28% |
| 29 | Gemma 4 31B | 98.56% | 95.89% | 99.80% | 100.00% | 85.23% |
| 30 | GPT-6 Sol | 98.56% | 96.86% | 98.83% | 100.00% | 90.05% |
| 31 | Grok 4.5 (Reasoning, Low) | 98.54% | 96.83% | 98.80% | 100.00% | 90.94% |
| 32 | GPT-5.1 | 98.54% | 97.43% | 98.18% | 100.00% | 90.73% |
| 33 | Gemini 3.1 Pro (Preview) | 98.51% | 96.51% | 99.03% | 100.00% | 94.08% |
| 34 | Aion 3.5 (Reasoning, High) | 98.49% | 97.58% | 99.08% | 98.81% | 91.90% |
| 35 | DeepSeek V4.1 Flash (Reasoning, High) | 98.47% | 96.80% | 98.62% | 100.00% | 94.30% |
| 36 | Muse Spark 1.3 (Reasoning, Medium) | 98.47% | 96.52% | 98.88% | 100.00% | 94.06% |
| 37 | GPT-5.6 Sol | 98.43% | 98.35% | 96.95% | 100.00% | 90.76% |
| 38 | GPT-5.4 (Reasoning) | 98.42% | 97.84% | 97.42% | 100.00% | 93.85% |
| 39 | ByteDance Seed 1.6 | 98.40% | 97.62% | 97.58% | 100.00% | 89.59% |
| 40 | GPT-6 Sol (Reasoning, Medium) | 98.37% | 96.59% | 98.52% | 100.00% | 92.63% |
| 41 | Gemini 3.6 Flash (Reasoning, Minimal) | 98.36% | 96.16% | 98.90% | 100.00% | 86.68% |
| 42 | Claude Opus 4.6 | 98.35% | 95.06% | 100.00% | 100.00% | 92.31% |
| 43 | Mistral Large 4.0 (Reasoning) | 98.35% | 96.60% | 98.44% | 100.00% | 92.14% |
| 44 | Ember-1 (Reasoning, Max) | 98.33% | 95.93% | 99.06% | 100.00% | 95.52% |
| 45 | Claude Sonnet 4.6 (Reasoning) | 98.30% | 95.84% | 99.06% | 100.00% | 93.64% |
| 46 | GPT-5.6 Sol (Reasoning, Medium) | 98.26% | 96.19% | 98.60% | 100.00% | 95.15% |
| 47 | Gemini 3.5 Flash (Reasoning, Minimal) | 98.26% | 96.60% | 98.17% | 100.00% | 85.88% |
| 48 | Gemma 4 26B (Reasoning) | 98.26% | 95.76% | 99.01% | 100.00% | 89.02% |
| 49 | Qwen 3.8 Flash (Reasoning) | 98.24% | 97.23% | 97.47% | 100.00% | 94.24% |
| 50 | Thinking Machines Inkling (Reasoning) | 98.23% | 96.68% | 98.01% | 100.00% | 90.78% |
| 51 | Z.AI GLM 4.7 | 98.22% | 95.98% | 98.67% | 100.00% | 87.67% |
| 52 | GPT-5.6 Terra | 98.21% | 95.69% | 98.95% | 100.00% | 88.23% |
| 53 | Claude Sonnet 5.5 (Reasoning) | 98.21% | 94.74% | 99.90% | 100.00% | 92.77% |
| 54 | Qwen 3.8 Max (Reasoning, XHigh) | 98.20% | 98.44% | 96.17% | 100.00% | 96.21% |
| 55 | GPT-5.5 | 98.20% | 96.02% | 98.59% | 100.00% | 89.37% |
| 56 | Grok 4.7 (Reasoning, High) | 98.17% | 95.42% | 99.11% | 100.00% | 92.62% |
| 57 | Z.AI GLM 5 Turbo | 98.17% | 96.68% | 97.83% | 100.00% | 93.29% |
| 58 | Gemini 3 Flash (Preview, Reasoning) | 98.12% | 96.17% | 98.19% | 100.00% | 89.93% |
| 59 | Gemini 2.5 Flash (Reasoning) | 98.12% | 96.95% | 97.39% | 100.00% | 84.14% |
| 60 | GPT-5.6 Terra (Reasoning, Medium) | 98.11% | 95.65% | 98.67% | 100.00% | 92.49% |
| 61 | Qwen 3.5 Plus (2026-02-15) | 98.10% | 94.91% | 99.38% | 100.00% | 86.17% |
| 62 | Qwen 3.7 Max | 98.08% | 95.96% | 98.27% | 100.00% | 94.55% |
| 63 | Claude Opus 5 | 98.06% | 95.08% | 99.11% | 100.00% | 89.97% |
| 64 | Qwen 3.5 397B A17B | 98.05% | 97.78% | 96.38% | 100.00% | 91.09% |
| 65 | Xiaomi MIMO v2.6 Pro | 98.05% | 95.18% | 98.98% | 100.00% | 91.50% |
| 66 | GPT-5.4 (Reasoning, Low) | 98.01% | 96.83% | 97.21% | 100.00% | 90.91% |
| 67 | Kimi K2.6 | 98.00% | 96.37% | 98.83% | 98.81% | 92.57% |
| 68 | DeepSeek V4 Pro | 97.98% | 95.32% | 98.62% | 100.00% | 82.05% |
| 69 | Claude Sonnet 5 (Reasoning, Low) | 97.93% | 94.42% | 99.36% | 100.00% | 90.16% |
| 70 | Claude Sonnet 5 (Reasoning) | 97.89% | 94.43% | 99.23% | 100.00% | 90.40% |
| 71 | GPT-6 Luna (Reasoning, Medium) | 97.87% | 95.20% | 98.41% | 100.00% | 92.40% |
| 72 | Gemini 2.5 Flash | 97.83% | 94.82% | 98.67% | 100.00% | 80.61% |
| 73 | Thinking Machines Inkling Small (Reasoning, High) | 97.82% | 96.49% | 96.96% | 100.00% | 87.39% |
| 74 | Kimi K2.5 | 97.79% | 96.37% | 98.19% | 98.81% | 90.86% |
| 75 | Gemini 3.5 Flash (Reasoning) | 97.78% | 98.44% | 98.47% | 96.43% | 93.35% |
| 76 | Z.AI GLM 4.6 | 97.78% | 95.02% | 98.31% | 100.00% | 87.64% |
| 77 | GPT-5.6 Luna (Reasoning, Medium) | 97.77% | 95.08% | 98.24% | 100.00% | 90.61% |
| 78 | Muse Spark 1.2 (Reasoning, Medium) | 97.76% | 96.11% | 98.37% | 98.81% | 94.71% |
| 79 | Kimi K3 (Reasoning, Low) | 97.74% | 94.14% | 99.08% | 100.00% | 92.07% |
| 80 | Aion 3.0 | 97.73% | 97.84% | 98.93% | 96.43% | 88.78% |
| 81 | Qwen 3.5 Plus (2026-04-20) | 97.70% | 96.29% | 96.81% | 100.00% | 89.79% |
| 82 | Claude Opus 4.5 | 97.69% | 93.08% | 100.00% | 100.00% | 89.60% |
| 83 | Qwen 3.8 27B (Reasoning, XHigh) | 97.68% | 95.65% | 97.37% | 100.00% | 92.91% |
| 84 | Claude Sonnet 5 | 97.65% | 93.58% | 99.36% | 100.00% | 87.34% |
| 85 | Grok 4.3 (Reasoning) | 97.64% | 96.47% | 97.63% | 98.81% | 90.99% |
| 86 | Xiaomi MIMO v2.6 Flash | 97.60% | 94.18% | 98.61% | 100.00% | 87.31% |
| 87 | Muse Spark 1.1 (Reasoning, Minimal) | 97.60% | 95.67% | 98.32% | 98.81% | 91.43% |
| 88 | Aion 3.5 Mini (Reasoning, High) | 97.59% | 94.04% | 98.72% | 100.00% | 92.36% |
| 89 | Claude Opus 4.7 (Reasoning) | 97.58% | 92.89% | 99.85% | 100.00% | 92.53% |
| 90 | Claude Opus 4.7 | 97.55% | 92.82% | 99.85% | 100.00% | 89.90% |
| 91 | GPT-5.2 | 97.54% | 96.25% | 96.38% | 100.00% | 89.45% |
| 92 | Gemini 3 Flash (Preview) | 97.54% | 93.70% | 98.90% | 100.00% | 85.47% |
| 93 | MiniMax M3 | 97.51% | 93.99% | 98.55% | 100.00% | 90.45% |
| 94 | GPT-6 Luna | 97.46% | 93.25% | 99.13% | 100.00% | 83.73% |
| 95 | Kimi K3 (Reasoning, High) | 97.42% | 93.14% | 99.11% | 100.00% | 92.99% |
| 96 | Gemini 3.1 Flash Lite | 97.35% | 93.93% | 98.11% | 100.00% | 85.09% |
| 97 | Claude Opus 4 | 97.25% | 93.42% | 98.34% | 100.00% | 87.22% |
| 98 | GPT-6 Luna (Reasoning, High) | 97.19% | 93.98% | 97.60% | 100.00% | 93.95% |
| 99 | Claude Haiku 5.5 (Adaptive) | 97.15% | 92.73% | 98.72% | 100.00% | 89.37% |
| 100 | GPT-5 Mini | 97.13% | 93.87% | 97.51% | 100.00% | 91.31% |
| 101 | Gemma 4 26B | 97.04% | 91.43% | 99.69% | 100.00% | 84.89% |
| 102 | GPT-6.1 Sol (Reasoning, Medium) | 97.04% | 98.12% | 92.98% | 100.00% | 95.88% |
| 103 | Claude Opus 5 (Reasoning, Low) | 96.99% | 91.61% | 99.36% | 100.00% | 92.06% |
| 104 | Claude Opus 5 (Reasoning) | 96.91% | 91.00% | 99.74% | 100.00% | 91.15% |
| 105 | Muse Glimmer 30B (Reasoning, Medium) | 96.91% | 92.10% | 98.63% | 100.00% | 88.81% |
| 106 | Gemini 3.1 Flash Lite (Reasoning) | 96.90% | 92.71% | 97.98% | 100.00% | 85.91% |
| 107 | Claude Haiku 4.5 | 96.81% | 90.77% | 99.64% | 100.00% | 83.36% |
| 108 | GPT-5.4 | 96.73% | 94.09% | 96.10% | 100.00% | 84.31% |
| 109 | Gemini 4 Argon (Reasoning, Medium) | 96.47% | 97.44% | 91.96% | 100.00% | 93.81% |
| 110 | Gemini 3.1 Flash Lite (Preview) | 96.46% | 91.27% | 98.12% | 100.00% | 85.41% |
| 111 | Claude Sonnet 4.6 | 96.37% | 89.29% | 99.82% | 100.00% | 90.66% |
| 112 | Qwen 3.5 122B | 96.31% | 91.84% | 98.28% | 98.81% | 90.32% |
| 113 | DeepSeek V4 Flash (Reasoning) | 96.15% | 94.95% | 98.26% | 95.24% | 88.06% |
| 114 | Qwen 3.6 Flash | 96.09% | 91.94% | 97.52% | 98.81% | 89.31% |
| 115 | Mistral Medium 3.5 | 96.03% | 90.78% | 97.32% | 100.00% | 84.52% |
| 116 | MiniMax M2.5 | 96.02% | 90.05% | 98.01% | 100.00% | 86.71% |
| 117 | Xiaomi MIMO v2.5 Pro | 95.96% | 91.14% | 96.73% | 100.00% | 86.05% |
| 118 | Mistral Medium 3.5 (Reasoning) | 95.83% | 90.03% | 97.45% | 100.00% | 85.32% |
| 119 | GPT-5.4 Mini (Reasoning) | 95.78% | 93.03% | 95.50% | 98.81% | 89.82% |
| 120 | DeepSeek V3.2 | 95.78% | 95.62% | 91.71% | 100.00% | 82.22% |
| 121 | Claude Haiku 5.5 (Reasoning, Low) | 95.77% | 88.83% | 99.67% | 98.81% | 84.75% |
| 122 | Mistral Large 4.0 | 95.72% | 88.42% | 98.75% | 100.00% | 84.72% |
| 123 | Grok 4.20 | 95.63% | 89.78% | 97.12% | 100.00% | 81.21% |
| 124 | GPT-4.1 Mini | 95.62% | 89.26% | 97.60% | 100.00% | 81.40% |
| 125 | GPT-5.6 Luna | 95.60% | 89.19% | 97.60% | 100.00% | 85.06% |
| 126 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 95.40% | 89.67% | 96.53% | 100.00% | 84.45% |
| 127 | Claude Haiku 5.5 (Reasoning, Medium) | 95.35% | 89.67% | 98.75% | 97.62% | 84.17% |
| 128 | Xiaomi MIMO v2.5 | 95.34% | 87.99% | 98.04% | 100.00% | 83.95% |
| 129 | Aion 2.0 | 95.34% | 93.58% | 97.21% | 95.24% | 86.66% |
| 130 | Z.AI GLM 4.5 | 95.32% | 95.45% | 91.69% | 98.81% | 84.95% |
| 131 | Qwen 3.6 35B | 95.10% | 90.37% | 97.30% | 97.62% | 87.66% |
| 132 | ByteDance Seed 2.0 Lite | 95.03% | 88.71% | 97.58% | 98.81% | 84.27% |
| 133 | Qwen 3.5 35B | 94.95% | 91.82% | 94.21% | 98.81% | 87.01% |
| 134 | Gemini 3.5 Flash Lite (Reasoning) | 94.93% | 88.15% | 96.63% | 100.00% | 84.34% |
| 135 | DeepSeek V4 Flash 0731 (Reasoning, High) | 94.92% | 90.20% | 95.74% | 98.81% | 87.97% |
| 136 | Gemini 2.5 Flash Lite (Reasoning) | 94.54% | 94.57% | 89.04% | 100.00% | 83.10% |
| 137 | GPT-4.1 | 94.40% | 86.53% | 96.66% | 100.00% | 86.82% |
| 138 | Z.AI GLM 4.5 Air | 94.38% | 86.09% | 97.05% | 100.00% | 80.74% |
| 139 | o4 Mini High | 94.36% | 87.18% | 97.09% | 98.81% | 88.78% |
| 140 | Mistral Large 2 | 94.16% | 90.87% | 91.61% | 100.00% | 81.50% |
| 141 | Mistral Large 3 | 94.09% | 90.68% | 91.61% | 100.00% | 84.29% |
| 142 | Qwen 3.6 27B | 93.97% | 88.52% | 95.77% | 97.62% | 88.33% |
| 143 | GPT-4o, Aug. 6th (temp=0) | 93.77% | 88.11% | 96.79% | 96.43% | 82.18% |
| 144 | Mistral Medium 3.1 | 93.77% | 84.76% | 96.56% | 100.00% | 76.08% |
| 145 | DeepSeek V4 Pro 0813 (Reasoning, High) | 93.76% | 92.48% | 96.23% | 92.57% | 90.21% |
| 146 | Aion 3.0 Mini | 93.65% | 91.12% | 95.78% | 94.05% | 83.69% |
| 147 | DeepSeek V3 (2024-12-26) | 93.58% | 89.33% | 92.60% | 98.81% | 82.62% |
| 148 | DeepSeek V4 Flash | 93.25% | 89.68% | 90.06% | 100.00% | 82.02% |
| 149 | Thinking Machines Inkling | 93.22% | 85.70% | 93.95% | 100.00% | 73.96% |
| 150 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 92.97% | 88.31% | 96.53% | 94.05% | 88.76% |
| 151 | Qwen 3.5 Flash | 92.80% | 88.93% | 93.04% | 96.43% | 85.66% |
| 152 | Qwen 3.7 Flash (Reasoning) | 92.63% | 81.34% | 96.55% | 100.00% | 88.56% |
| 153 | GPT-5.4 Mini (Reasoning, Low) | 92.63% | 85.94% | 91.94% | 100.00% | 83.57% |
| 154 | MiniMax M2.7 | 92.14% | 82.95% | 95.84% | 97.62% | 86.23% |
| 155 | Gemini 2.5 Flash Lite | 92.13% | 84.21% | 92.17% | 100.00% | 79.91% |
| 156 | Llama 3.1 70B | 92.10% | 84.01% | 94.67% | 97.62% | 77.41% |
| 157 | Qwen 3 235B A22B Instruct 2507 | 91.75% | 79.66% | 95.60% | 100.00% | 78.07% |
| 158 | GPT-OSS 120B | 91.73% | 83.23% | 94.34% | 97.62% | 84.81% |
| 159 | ByteDance Seed 1.6 Flash | 91.64% | 81.97% | 95.32% | 97.62% | 70.92% |
| 160 | Laguna S 2.1 | 91.27% | 86.03% | 87.78% | 100.00% | 79.99% |
| 161 | Writer: Palmyra X5 | 91.20% | 79.31% | 94.28% | 100.00% | 78.11% |
| 162 | ByteDance Seed 2.0 Mini | 91.08% | 86.72% | 90.10% | 96.43% | 85.69% |
| 163 | Mistral Small 4 | 91.00% | 81.54% | 91.45% | 100.00% | 75.23% |
| 164 | DeepSeek-V2 Chat | 90.90% | 83.56% | 91.53% | 97.62% | 84.09% |
| 165 | o4 Mini | 90.61% | 77.98% | 96.24% | 97.62% | 86.56% |
| 166 | GPT-5.4 Mini | 90.60% | 83.34% | 88.47% | 100.00% | 80.45% |
| 167 | Mistral Small 4 (Reasoning) | 90.58% | 79.45% | 93.47% | 98.81% | 79.48% |
| 168 | Grok 4.3 | 90.19% | 81.66% | 88.90% | 100.00% | 78.00% |
| 169 | Qwen 3 32B | 89.95% | 77.20% | 93.83% | 98.81% | 79.37% |
| 170 | DeepSeek V3 (2025-03-24) | 89.57% | 79.33% | 90.56% | 98.81% | 79.93% |
| 171 | Mistral Small 3.2 24B | 89.48% | 76.07% | 92.38% | 100.00% | 77.36% |
| 172 | Qwen 2.5 72B | 89.18% | 71.74% | 95.78% | 100.00% | 73.17% |
| 173 | Hermes 3 405B | 89.14% | 69.94% | 97.48% | 100.00% | 80.80% |
| 174 | WizardLM 2 8x22b | 88.13% | 81.62% | 89.67% | 93.12% | 71.45% |
| 175 | Laguna XS 2.1 | 87.94% | 72.75% | 92.26% | 98.81% | 75.42% |
| 176 | DeepSeek V3.1 | 87.27% | 81.88% | 84.70% | 95.24% | 82.35% |
| 177 | GPT-4o, Aug. 6th (temp=1) | 86.72% | 72.28% | 95.01% | 92.86% | 81.28% |
| 178 | Gemma 3 27B | 86.63% | 64.41% | 95.49% | 100.00% | 75.70% |
| 179 | Nemotron 3 Super | 86.34% | 79.06% | 89.49% | 90.48% | 81.69% |
| 180 | Ministral 3 14B | 86.20% | 69.48% | 89.12% | 100.00% | 70.45% |
| 181 | Cydonia 24B V4.1 | 86.15% | 65.80% | 92.65% | 100.00% | 72.68% |
| 182 | Z.AI GLM 4.7 Flash | 85.82% | 70.63% | 90.40% | 96.43% | 82.21% |
| 183 | GPT-4o Mini (temp=1) | 85.78% | 70.40% | 86.94% | 100.00% | 77.82% |
| 184 | Qwen 3.5 9B | 85.35% | 71.91% | 92.48% | 91.67% | 84.05% |
| 185 | Inception Mercury 2 | 85.26% | 70.42% | 91.31% | 94.05% | 81.99% |
| 186 | Gemma 3 12B | 85.18% | 67.87% | 87.66% | 100.00% | 76.07% |
| 187 | GPT-4o Mini (temp=0) | 84.62% | 67.00% | 86.87% | 100.00% | 76.86% |
| 188 | GPT-5.4 Nano (Reasoning) | 83.32% | 59.85% | 90.10% | 100.00% | 80.02% |
| 189 | GPT-5 Nano | 82.74% | 61.06% | 91.91% | 95.24% | 80.16% |
| 190 | GPT-5.4 Nano (Reasoning, Low) | 82.23% | 61.68% | 85.00% | 100.00% | 77.46% |
| 191 | GPT-5.4 Nano | 79.22% | 53.44% | 84.23% | 100.00% | 72.16% |
| 192 | Ministral 3 8B | 78.52% | 52.05% | 83.53% | 100.00% | 69.98% |
| 193 | Gemma 3 4B | 78.38% | 40.80% | 94.35% | 100.00% | 66.33% |
| 194 | Ministral 8B | 77.52% | 48.88% | 83.69% | 100.00% | 63.77% |
| 195 | GPT-4.1 Nano | 76.06% | 50.14% | 78.02% | 100.00% | 69.90% |
| 196 | Nemotron 3 Nano | 75.81% | 62.02% | 78.40% | 87.00% | 74.50% |
| 197 | Arcee AI: Trinity Mini | 73.88% | 50.86% | 85.07% | 85.71% | 67.68% |
| 198 | Mistral NeMO | 73.69% | 45.51% | 82.35% | 93.21% | 63.80% |
| 199 | Ministral 3B | 70.91% | 40.57% | 74.55% | 97.62% | 59.25% |
| 200 | Ministral 3 3B | 69.80% | 39.84% | 73.12% | 96.43% | 65.02% |
| 201 | Cohere Command R+ (Aug. 2024) | 68.40% | 39.15% | 70.67% | 95.39% | 67.04% |
| 202 | Hermes 3 70B | 63.34% | 44.57% | 66.87% | 78.57% | 69.74% |