Text Editing
18 scenarios across 3 subcategories. 154 models scored.
Subcategories
| Subcategory | Avg Score | Best Model | Best Score |
|---|---|---|---|
| Transformation | 83.94% | Gemini 3.5 Flash (Reasoning) | 98.44% |
| Preservation | 93.68% | Claude Opus 4.6 | 100.00% |
| Structural Integrity | 98.32% | Qwen3.7 Max | 100.00% |
Model Leaderboard
All models ranked by their Text Editing category score.
| # | Model | Text Editing | Transformation | Preservation | Structural Integrity | Overall |
|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 4 | 99.13% | 97.70% | 99.69% | 100.00% | 88.72% |
| 2 | Claude Sonnet 4.5 | 99.02% | 97.74% | 99.31% | 100.00% | 88.03% |
| 3 | Z.AI GLM 5.1 | 98.90% | 97.82% | 98.88% | 100.00% | 94.37% |
| 4 | GPT-5 | 98.90% | 98.11% | 98.57% | 100.00% | 91.93% |
| 5 | Gemini 3 Pro (Preview) | 98.86% | 98.12% | 98.47% | 100.00% | 88.79% |
| 6 | Claude Opus 4.6 (Reasoning) | 98.86% | 97.85% | 98.72% | 100.00% | 95.02% |
| 7 | Grok 4.20 (Reasoning) | 98.83% | 97.60% | 98.90% | 100.00% | 91.39% |
| 8 | Gemma 4 31B (Reasoning) | 98.83% | 97.51% | 98.98% | 100.00% | 91.71% |
| 9 | GPT-5.5 (Reasoning) | 98.79% | 97.78% | 98.57% | 100.00% | 92.98% |
| 10 | Claude Opus 4.8 (Reasoning) | 98.78% | 96.33% | 100.00% | 100.00% | 92.22% |
| 11 | Grok 4 | 98.76% | 97.06% | 99.23% | 100.00% | 88.12% |
| 12 | Claude Opus 4.8 (Reasoning, Low) | 98.71% | 96.27% | 99.87% | 100.00% | 92.14% |
| 13 | Qwen 3.5 27B | 98.69% | 97.53% | 98.55% | 100.00% | 90.85% |
| 14 | Grok 4.20 (Beta, Reasoning) | 98.69% | 97.27% | 98.80% | 100.00% | 91.49% |
| 15 | Z.AI GLM 5 | 98.59% | 97.15% | 98.62% | 100.00% | 91.23% |
| 16 | GPT-5.5 (Reasoning, Low) | 98.59% | 96.83% | 98.93% | 100.00% | 92.59% |
| 17 | Qwen3.6 Max Preview | 98.58% | 96.97% | 98.78% | 100.00% | 94.54% |
| 18 | Gemini 2.5 Pro | 98.58% | 96.93% | 98.80% | 100.00% | 88.53% |
| 19 | DeepSeek V4 Pro (Reasoning) | 98.56% | 97.09% | 98.60% | 100.00% | 90.10% |
| 20 | Gemma 4 31B | 98.56% | 95.89% | 99.80% | 100.00% | 86.91% |
| 21 | GPT-5.1 | 98.54% | 97.43% | 98.18% | 100.00% | 92.54% |
| 22 | Gemini 3.1 Pro (Preview) | 98.51% | 96.51% | 99.03% | 100.00% | 94.37% |
| 23 | GPT-5.4 (Reasoning) | 98.42% | 97.84% | 97.42% | 100.00% | 93.24% |
| 24 | ByteDance Seed 1.6 | 98.40% | 97.62% | 97.58% | 100.00% | 90.70% |
| 25 | Claude Opus 4.6 | 98.35% | 95.06% | 100.00% | 100.00% | 92.35% |
| 26 | Claude Sonnet 4.6 (Reasoning) | 98.30% | 95.84% | 99.06% | 100.00% | 93.66% |
| 27 | Gemini 3.5 Flash (Reasoning, Minimal) | 98.26% | 96.60% | 98.17% | 100.00% | 86.47% |
| 28 | Gemma 4 26B (Reasoning) | 98.26% | 95.76% | 99.01% | 100.00% | 91.49% |
| 29 | Z.AI GLM 4.7 | 98.22% | 95.98% | 98.67% | 100.00% | 88.69% |
| 30 | GPT-5.5 | 98.20% | 96.02% | 98.59% | 100.00% | 89.09% |
| 31 | Z.AI GLM 5 Turbo | 98.17% | 96.68% | 97.83% | 100.00% | 94.27% |
| 32 | Gemini 3 Flash (Preview, Reasoning) | 98.12% | 96.17% | 98.19% | 100.00% | 90.50% |
| 33 | Gemini 2.5 Flash (Reasoning) | 98.12% | 96.95% | 97.39% | 100.00% | 86.51% |
| 34 | Qwen 3.5 Plus (2026-02-15) | 98.10% | 94.91% | 99.38% | 100.00% | 85.96% |
| 35 | Qwen3.7 Max | 98.08% | 95.96% | 98.27% | 100.00% | 95.75% |
| 36 | Qwen 3.5 397B A17B | 98.05% | 97.78% | 96.38% | 100.00% | 91.73% |
| 37 | GPT-5.4 (Reasoning, Low) | 98.01% | 96.83% | 97.21% | 100.00% | 91.41% |
| 38 | MoonshotAI: Kimi K2.6 | 98.00% | 96.37% | 98.83% | 98.81% | 92.31% |
| 39 | DeepSeek V4 Pro | 97.98% | 95.32% | 98.62% | 100.00% | 82.63% |
| 40 | Grok 4.1 Fast | 97.87% | 96.32% | 97.29% | 100.00% | 89.55% |
| 41 | Gemini 2.5 Flash | 97.83% | 94.82% | 98.67% | 100.00% | 80.60% |
| 42 | MoonshotAI: Kimi K2.5 | 97.79% | 96.37% | 98.19% | 98.81% | 91.04% |
| 43 | Gemini 3.5 Flash (Reasoning) | 97.78% | 98.44% | 98.47% | 96.43% | 94.08% |
| 44 | Z.AI GLM 4.6 | 97.78% | 95.02% | 98.31% | 100.00% | 89.11% |
| 45 | Qwen 3.5 Plus (2026-04-20) | 97.70% | 96.29% | 96.81% | 100.00% | 91.51% |
| 46 | Claude Opus 4.5 | 97.69% | 93.08% | 100.00% | 100.00% | 89.69% |
| 47 | Grok 4.3 (Reasoning) | 97.64% | 96.47% | 97.63% | 98.81% | 93.60% |
| 48 | Claude Opus 4.7 (Reasoning) | 97.58% | 92.89% | 99.85% | 100.00% | 93.23% |
| 49 | Claude Opus 4.7 | 97.55% | 92.82% | 99.85% | 100.00% | 89.93% |
| 50 | GPT-5.2 | 97.54% | 96.25% | 96.38% | 100.00% | 90.26% |
| 51 | Gemini 3 Flash (Preview) | 97.54% | 93.70% | 98.90% | 100.00% | 85.35% |
| 52 | MiniMax M3 | 97.51% | 93.99% | 98.55% | 100.00% | 90.88% |
| 53 | Gemini 3.1 Flash Lite | 97.35% | 93.93% | 98.11% | 100.00% | 85.75% |
| 54 | Grok 4 Fast | 97.26% | 93.19% | 98.60% | 100.00% | 86.15% |
| 55 | Claude Opus 4 | 97.25% | 93.42% | 98.34% | 100.00% | 87.69% |
| 56 | GPT-5 Mini | 97.13% | 93.87% | 97.51% | 100.00% | 92.62% |
| 57 | Claude 3.7 Sonnet | 97.12% | 93.64% | 97.73% | 100.00% | 83.39% |
| 58 | Gemma 4 26B | 97.04% | 91.43% | 99.69% | 100.00% | 85.84% |
| 59 | Gemini 3.1 Flash Lite (Reasoning) | 96.90% | 92.71% | 97.98% | 100.00% | 86.41% |
| 60 | Claude Haiku 4.5 | 96.81% | 90.77% | 99.64% | 100.00% | 85.14% |
| 61 | GPT-5.4 | 96.73% | 94.09% | 96.10% | 100.00% | 84.32% |
| 62 | Claude 3.5 Sonnet | 96.57% | 92.76% | 96.96% | 100.00% | 84.24% |
| 63 | Gemini 3.1 Flash Lite (Preview) | 96.46% | 91.27% | 98.12% | 100.00% | 85.87% |
| 64 | Claude Sonnet 4.6 | 96.37% | 89.29% | 99.82% | 100.00% | 91.15% |
| 65 | Qwen 3.5 122B | 96.31% | 91.84% | 98.28% | 98.81% | 91.53% |
| 66 | DeepSeek V4 Flash (Reasoning) | 96.15% | 94.95% | 98.26% | 95.24% | 89.01% |
| 67 | Qwen 3.6 Flash | 96.09% | 91.94% | 97.52% | 98.81% | 90.65% |
| 68 | Stealth: Healer Alpha | 96.04% | 90.26% | 97.86% | 100.00% | 85.93% |
| 69 | MiniMax M2.5 | 96.02% | 90.05% | 98.01% | 100.00% | 88.71% |
| 70 | Xiaomi MIMO v2.5 Pro | 95.96% | 91.14% | 96.73% | 100.00% | 87.36% |
| 71 | GPT-5.4 Mini (Reasoning) | 95.78% | 93.03% | 95.50% | 98.81% | 90.65% |
| 72 | DeepSeek V3.2 | 95.78% | 95.62% | 91.71% | 100.00% | 82.25% |
| 73 | Grok 4.20 | 95.63% | 89.78% | 97.12% | 100.00% | 81.70% |
| 74 | GPT-4.1 Mini | 95.62% | 89.26% | 97.60% | 100.00% | 83.20% |
| 75 | Stealth: Hunter Alpha | 95.53% | 91.32% | 96.45% | 98.81% | 87.34% |
| 76 | Grok 4.20 (Beta) | 95.49% | 92.06% | 94.41% | 100.00% | 83.85% |
| 77 | GPT-4o, May 13th (temp=0) | 95.35% | 87.89% | 98.16% | 100.00% | 85.36% |
| 78 | Xiaomi MIMO v2.5 | 95.34% | 87.99% | 98.04% | 100.00% | 85.05% |
| 79 | Aion 2.0 | 95.34% | 93.58% | 97.21% | 95.24% | 89.21% |
| 80 | Z.AI GLM 4.5 | 95.32% | 95.45% | 91.69% | 98.81% | 86.27% |
| 81 | Mistral Large | 95.14% | 90.77% | 94.67% | 100.00% | 80.15% |
| 82 | Qwen 3.6 35B | 95.10% | 90.37% | 97.30% | 97.62% | 89.05% |
| 83 | ByteDance Seed 2.0 Lite | 95.03% | 88.71% | 97.58% | 98.81% | 84.80% |
| 84 | Qwen 3.5 35B | 94.95% | 91.82% | 94.21% | 98.81% | 88.00% |
| 85 | Gemini 2.5 Flash Lite (Reasoning) | 94.54% | 94.57% | 89.04% | 100.00% | 85.75% |
| 86 | GPT-4.1 | 94.40% | 86.53% | 96.66% | 100.00% | 88.68% |
| 87 | Z.AI GLM 4.5 Air | 94.38% | 86.09% | 97.05% | 100.00% | 83.12% |
| 88 | o4 Mini High | 94.36% | 87.18% | 97.09% | 98.81% | 90.29% |
| 89 | Mistral Large 2 | 94.16% | 90.87% | 91.61% | 100.00% | 82.41% |
| 90 | Mistral Large 3 | 94.09% | 90.68% | 91.61% | 100.00% | 85.43% |
| 91 | Qwen 3.6 27B | 93.97% | 88.52% | 95.77% | 97.62% | 89.72% |
| 92 | GPT-4o, Aug. 6th (temp=0) | 93.77% | 88.11% | 96.79% | 96.43% | 82.45% |
| 93 | Mistral Medium 3.1 | 93.77% | 84.76% | 96.56% | 100.00% | 77.83% |
| 94 | DeepSeek V3 (2024-12-26) | 93.58% | 89.33% | 92.60% | 98.81% | 83.68% |
| 95 | DeepSeek V4 Flash | 93.25% | 89.68% | 90.06% | 100.00% | 82.02% |
| 96 | Qwen 3.5 Flash | 92.80% | 88.93% | 93.04% | 96.43% | 86.38% |
| 97 | GPT-5.4 Mini (Reasoning, Low) | 92.63% | 85.94% | 91.94% | 100.00% | 85.75% |
| 98 | GPT-4o, May 13th (temp=1) | 92.41% | 79.68% | 97.54% | 100.00% | 83.80% |
| 99 | MiniMax M2.7 | 92.14% | 82.95% | 95.84% | 97.62% | 89.10% |
| 100 | Gemini 2.5 Flash Lite | 92.13% | 84.21% | 92.17% | 100.00% | 81.08% |
| 101 | Llama 3.1 70B | 92.10% | 84.01% | 94.67% | 97.62% | 78.40% |
| 102 | Qwen3 235B A22B Instruct 2507 | 91.75% | 79.66% | 95.60% | 100.00% | 80.10% |
| 103 | GPT-OSS 120B | 91.73% | 83.23% | 94.34% | 97.62% | 86.44% |
| 104 | ByteDance Seed 1.6 Flash | 91.64% | 81.97% | 95.32% | 97.62% | 73.27% |
| 105 | Writer: Palmyra X5 | 91.20% | 79.31% | 94.28% | 100.00% | 79.57% |
| 106 | ByteDance Seed 2.0 Mini | 91.08% | 86.72% | 90.10% | 96.43% | 86.91% |
| 107 | Mistral Small 4 | 91.00% | 81.54% | 91.45% | 100.00% | 76.46% |
| 108 | DeepSeek-V2 Chat | 90.90% | 83.56% | 91.53% | 97.62% | 84.83% |
| 109 | o4 Mini | 90.61% | 77.98% | 96.24% | 97.62% | 88.35% |
| 110 | GPT-5.4 Mini | 90.60% | 83.34% | 88.47% | 100.00% | 82.43% |
| 111 | Mistral Small 4 (Reasoning) | 90.58% | 79.45% | 93.47% | 98.81% | 82.39% |
| 112 | Mistral Small Creative | 90.31% | 73.96% | 96.98% | 100.00% | 73.27% |
| 113 | Grok 4.3 | 90.19% | 81.66% | 88.90% | 100.00% | 78.66% |
| 114 | Qwen 3 32B | 89.95% | 77.20% | 93.83% | 98.81% | 82.21% |
| 115 | DeepSeek V3 (2025-03-24) | 89.57% | 79.33% | 90.56% | 98.81% | 81.99% |
| 116 | Mistral Small 3.2 24B | 89.48% | 76.07% | 92.38% | 100.00% | 78.58% |
| 117 | Qwen 2.5 72B | 89.18% | 71.74% | 95.78% | 100.00% | 75.46% |
| 118 | Hermes 3 405B | 89.14% | 69.94% | 97.48% | 100.00% | 82.86% |
| 119 | WizardLM 2 8x22b | 88.13% | 81.62% | 89.67% | 93.12% | 71.06% |
| 120 | DeepSeek V3.1 | 87.27% | 81.88% | 84.70% | 95.24% | 82.39% |
| 121 | Llama 3.1 Nemotron 70B | 87.26% | 73.30% | 93.45% | 95.04% | 74.70% |
| 122 | GPT-4o, Aug. 6th (temp=1) | 86.72% | 72.28% | 95.01% | 92.86% | 82.62% |
| 123 | Gemma 3 27B | 86.63% | 64.41% | 95.49% | 100.00% | 77.85% |
| 124 | Arcee AI: Trinity Large (Preview) | 86.62% | 76.70% | 83.17% | 100.00% | 73.33% |
| 125 | Nemotron 3 Super | 86.34% | 79.06% | 89.49% | 90.48% | 84.56% |
| 126 | Ministral 3 14B | 86.20% | 69.48% | 89.12% | 100.00% | 72.54% |
| 127 | Cydonia 24B V4.1 | 86.15% | 65.80% | 92.65% | 100.00% | 75.09% |
| 128 | Z.AI GLM 4.7 Flash | 85.82% | 70.63% | 90.40% | 96.43% | 84.82% |
| 129 | GPT-4o Mini (temp=1) | 85.78% | 70.40% | 86.94% | 100.00% | 79.08% |
| 130 | Qwen 3.5 9B | 85.35% | 71.91% | 92.48% | 91.67% | 86.05% |
| 131 | Inception Mercury 2 | 85.26% | 70.42% | 91.31% | 94.05% | 83.85% |
| 132 | Gemma 3 12B | 85.18% | 67.87% | 87.66% | 100.00% | 78.41% |
| 133 | GPT-4o Mini (temp=0) | 84.62% | 67.00% | 86.87% | 100.00% | 78.29% |
| 134 | GPT-5.4 Nano (Reasoning) | 83.32% | 59.85% | 90.10% | 100.00% | 81.36% |
| 135 | GPT-5 Nano | 82.74% | 61.06% | 91.91% | 95.24% | 82.60% |
| 136 | GPT-5.4 Nano (Reasoning, Low) | 82.23% | 61.68% | 85.00% | 100.00% | 79.48% |
| 137 | Inception Mercury | 79.53% | 58.12% | 87.15% | 93.32% | 79.50% |
| 138 | GPT-5.4 Nano | 79.22% | 53.44% | 84.23% | 100.00% | 74.40% |
| 139 | Ministral 3 8B | 78.52% | 52.05% | 83.53% | 100.00% | 71.76% |
| 140 | Gemma 3 4B | 78.38% | 40.80% | 94.35% | 100.00% | 68.57% |
| 141 | Ministral 8B | 77.52% | 48.88% | 83.69% | 100.00% | 64.87% |
| 142 | Skyfall 36B V2 | 76.69% | 55.99% | 82.94% | 91.15% | 65.76% |
| 143 | GPT-4.1 Nano | 76.06% | 50.14% | 78.02% | 100.00% | 71.94% |
| 144 | Nemotron 3 Nano | 75.81% | 62.02% | 78.40% | 87.00% | 77.73% |
| 145 | Llama 3.1 8B | 75.45% | 51.53% | 80.76% | 94.05% | 63.35% |
| 146 | Arcee AI: Trinity Mini | 73.88% | 50.86% | 85.07% | 85.71% | 70.90% |
| 147 | Mistral NeMO | 73.69% | 45.51% | 82.35% | 93.21% | 65.04% |
| 148 | LFM2 24B | 71.56% | 66.33% | 57.43% | 90.94% | 58.77% |
| 149 | Ministral 3B | 70.91% | 40.57% | 74.55% | 97.62% | 61.29% |
| 150 | Ministral 3 3B | 69.80% | 39.84% | 73.12% | 96.43% | 67.22% |
| 151 | Cohere Command R+ (Aug. 2024) | 68.40% | 39.15% | 70.67% | 95.39% | 69.03% |
| 152 | Claude 3 Haiku | 64.36% | 48.58% | 63.45% | 81.03% | 71.19% |
| 153 | Hermes 3 70B | 63.34% | 44.57% | 66.87% | 78.57% | 72.57% |
| 154 | Rocinante 12B | 56.31% | 32.19% | 63.96% | 72.78% | 54.54% |