Dialogue
Subcategory of Creative Writing. 155 models scored.
Model Leaderboard
All models ranked by their Dialogue subcategory score.
| # | Model | Dialogue | Creative Writing | Overall |
|---|---|---|---|---|
| 1 | GPT-5.5 (Reasoning, Low) | 96.25% | 90.24% | 92.59% |
| 2 | GPT-5.5 | 95.32% | 90.39% | 89.09% |
| 3 | Claude Sonnet 4.6 | 95.20% | 83.31% | 91.15% |
| 4 | Claude Sonnet 4.6 (Reasoning) | 94.92% | 83.09% | 93.66% |
| 5 | GPT-5.5 (Reasoning) | 94.90% | 90.26% | 92.98% |
| 6 | GPT-5.4 | 94.79% | 90.94% | 84.32% |
| 7 | MiniMax M3 | 93.86% | 84.57% | 90.88% |
| 8 | GPT-5.4 (Reasoning) | 93.69% | 91.17% | 93.24% |
| 9 | Claude Opus 4.6 (Reasoning) | 93.56% | 84.55% | 95.02% |
| 10 | Z.AI GLM 5 Turbo | 93.23% | 84.66% | 94.27% |
| 11 | MoonshotAI: Kimi K2.6 | 92.60% | 85.47% | 92.31% |
| 12 | Qwen 3.5 397B A17B | 92.54% | 86.93% | 91.73% |
| 13 | Z.AI GLM 5.1 | 92.52% | 84.05% | 94.37% |
| 14 | Claude Opus 4.6 | 92.37% | 83.59% | 92.35% |
| 15 | GPT-5.4 (Reasoning, Low) | 92.18% | 90.51% | 91.41% |
| 16 | Qwen 3.5 9B | 91.95% | 84.35% | 86.05% |
| 17 | Qwen3.6 Max Preview | 91.85% | 88.42% | 94.54% |
| 18 | DeepSeek V4 Pro | 91.48% | 83.70% | 82.63% |
| 19 | GPT-5 | 91.30% | 86.87% | 91.93% |
| 20 | Grok 4.3 (Reasoning) | 90.45% | 85.11% | 93.60% |
| 21 | GPT-5.4 Mini | 90.45% | 88.10% | 82.43% |
| 22 | GPT-5.4 Mini (Reasoning) | 90.04% | 88.66% | 90.65% |
| 23 | GPT-5.4 Mini (Reasoning, Low) | 89.66% | 87.72% | 85.75% |
| 24 | Claude Sonnet 4.5 | 89.63% | 84.19% | 88.03% |
| 25 | Qwen 3.5 35B | 89.61% | 83.51% | 88.00% |
| 26 | Claude Opus 4 | 89.08% | 83.79% | 87.69% |
| 27 | Qwen 3.6 35B | 89.07% | 85.97% | 89.05% |
| 28 | Qwen3.7 Max | 88.93% | 85.39% | 95.75% |
| 29 | MiniMax M2.5 | 88.93% | 81.21% | 88.71% |
| 30 | MiniMax M2.7 | 88.91% | 81.70% | 89.10% |
| 31 | Claude Opus 4.5 | 88.91% | 81.71% | 89.69% |
| 32 | Qwen 3.5 27B | 88.67% | 82.54% | 90.85% |
| 33 | Claude Opus 4.7 | 88.63% | 84.74% | 89.93% |
| 34 | DeepSeek V4 Flash | 88.48% | 83.42% | 82.02% |
| 35 | Z.AI GLM 5 | 88.46% | 83.63% | 91.23% |
| 36 | Claude Opus 4.7 (Reasoning) | 88.14% | 84.73% | 93.23% |
| 37 | DeepSeek V4 Flash (Reasoning) | 88.10% | 83.03% | 89.01% |
| 38 | Claude Opus 4.8 (Reasoning, Low) | 87.92% | 85.86% | 92.14% |
| 39 | GPT-5.1 | 87.44% | 87.20% | 92.54% |
| 40 | Qwen3 235B A22B Instruct 2507 | 87.23% | 84.81% | 80.10% |
| 41 | Gemini 3.1 Pro (Preview) | 87.20% | 85.44% | 94.37% |
| 42 | Grok 4.3 | 87.13% | 84.51% | 78.66% |
| 43 | Qwen 3.5 Flash | 87.13% | 83.81% | 86.38% |
| 44 | Qwen 3.5 122B | 86.76% | 83.02% | 91.53% |
| 45 | Qwen 3.6 Flash | 86.74% | 86.02% | 90.65% |
| 46 | Claude Opus 4.8 (Reasoning) | 86.50% | 85.25% | 92.22% |
| 47 | MoonshotAI: Kimi K2.5 | 86.21% | 81.35% | 91.04% |
| 48 | ByteDance Seed 2.0 Lite | 85.96% | 82.35% | 84.80% |
| 49 | GPT-5 Mini | 85.94% | 80.48% | 92.62% |
| 50 | ByteDance Seed 1.6 | 85.62% | 78.43% | 90.70% |
| 51 | Mistral Small 4 (Reasoning) | 85.39% | 81.67% | 82.39% |
| 52 | Qwen 3.5 Plus (2026-04-20) | 85.08% | 85.18% | 91.51% |
| 53 | GPT-5.4 Nano (Reasoning) | 85.05% | 80.97% | 81.36% |
| 54 | Writer: Palmyra X5 | 84.42% | 83.95% | 79.57% |
| 55 | DeepSeek V4 Pro (Reasoning) | 84.25% | 82.99% | 90.10% |
| 56 | DeepSeek V3 (2025-03-24) | 83.31% | 82.34% | 81.99% |
| 57 | Grok 4.20 (Reasoning) | 83.26% | 86.25% | 91.39% |
| 58 | GPT-5.4 Nano | 83.18% | 80.50% | 74.40% |
| 59 | GPT-5.4 Nano (Reasoning, Low) | 83.10% | 80.93% | 79.48% |
| 60 | Mistral Large 2 | 83.10% | 81.86% | 82.41% |
| 61 | Claude Sonnet 4 | 82.84% | 79.21% | 88.72% |
| 62 | Mistral Small 4 | 82.49% | 81.12% | 76.46% |
| 63 | Claude Haiku 4.5 | 82.25% | 78.96% | 85.14% |
| 64 | Mistral Large | 81.53% | 82.02% | 80.15% |
| 65 | Mistral Medium 3.1 | 81.51% | 81.70% | 77.83% |
| 66 | Gemma 4 26B (Reasoning) | 81.41% | 76.38% | 91.49% |
| 67 | ByteDance Seed 2.0 Mini | 81.36% | 80.11% | 86.91% |
| 68 | Gemini 3.1 Flash Lite (Reasoning) | 81.09% | 76.31% | 86.41% |
| 69 | Grok 4.20 (Beta, Reasoning) | 80.80% | 84.50% | 91.49% |
| 70 | GPT-5.2 | 80.71% | 80.36% | 90.26% |
| 71 | Mistral Large 3 | 80.22% | 81.21% | 85.43% |
| 72 | Claude 3.5 Sonnet | 80.13% | 78.69% | 84.24% |
| 73 | Gemma 4 31B (Reasoning) | 80.03% | 78.13% | 91.71% |
| 74 | ByteDance Seed 1.6 Flash | 79.96% | 81.51% | 73.27% |
| 75 | Xiaomi MIMO v2.5 Pro | 79.81% | 81.08% | 87.36% |
| 76 | Grok 4.1 Fast | 78.96% | 82.14% | 89.55% |
| 77 | Gemini 3.1 Flash Lite | 78.90% | 76.01% | 85.75% |
| 78 | o4 Mini | 78.87% | 82.04% | 88.35% |
| 79 | Qwen 3 32B | 78.83% | 81.30% | 82.21% |
| 80 | Mistral Small Creative | 78.30% | 80.29% | 73.27% |
| 81 | o4 Mini High | 78.26% | 82.72% | 90.29% |
| 82 | Qwen 3.6 27B | 78.25% | 82.81% | 89.72% |
| 83 | WizardLM 2 8x22b | 77.45% | 79.06% | 71.06% |
| 84 | Gemini 2.5 Pro | 77.40% | 81.03% | 88.53% |
| 85 | Xiaomi MIMO v2.5 | 77.40% | 79.16% | 85.05% |
| 86 | Stealth: Healer Alpha | 77.16% | 78.28% | 85.93% |
| 87 | Grok 4.20 | 77.13% | 83.44% | 81.70% |
| 88 | GPT-4.1 | 76.96% | 81.24% | 88.68% |
| 89 | Aion 2.0 | 76.51% | 80.24% | 89.21% |
| 90 | Stealth: Hunter Alpha | 76.41% | 79.18% | 87.34% |
| 91 | Ministral 8B | 76.29% | 76.87% | 64.87% |
| 92 | Gemini 3.1 Flash Lite (Preview) | 75.91% | 75.78% | 85.87% |
| 93 | Ministral 3B | 75.29% | 75.49% | 61.29% |
| 94 | Claude 3.7 Sonnet | 75.00% | 76.31% | 83.39% |
| 95 | Ministral 3 14B | 74.59% | 79.11% | 72.54% |
| 96 | Ministral 3 3B | 74.49% | 75.45% | 67.22% |
| 97 | Skyfall 36B V2 | 74.44% | 83.32% | 65.76% |
| 98 | Z.AI GLM 4.6 | 74.32% | 78.86% | 89.11% |
| 99 | Grok 4.20 (Beta) | 74.11% | 82.80% | 83.85% |
| 100 | Gemma 4 26B | 73.77% | 75.17% | 85.84% |
| 101 | DeepSeek V3.2 | 73.33% | 79.95% | 82.25% |
| 102 | Inception Mercury | 73.29% | 69.99% | 79.50% |
| 103 | Z.AI GLM 4.5 | 73.22% | 76.56% | 86.27% |
| 104 | Llama 3.1 8B | 73.18% | 76.54% | 63.35% |
| 105 | Ministral 3 8B | 72.81% | 77.26% | 71.76% |
| 106 | Rocinante 12B | 72.56% | 81.94% | 54.54% |
| 107 | LFM2 24B | 72.22% | 78.10% | 58.77% |
| 108 | Z.AI GLM 4.7 | 71.01% | 78.89% | 88.69% |
| 109 | Llama 3.1 70B | 70.76% | 72.78% | 78.40% |
| 110 | Gemini 2.5 Flash | 70.64% | 77.57% | 80.60% |
| 111 | Gemma 4 31B | 70.38% | 75.59% | 86.91% |
| 112 | DeepSeek V3 (2024-12-26) | 69.79% | 77.88% | 83.68% |
| 113 | Z.AI GLM 4.7 Flash | 69.49% | 77.36% | 84.82% |
| 114 | Gemini 3 Flash (Preview, Reasoning) | 69.48% | 75.87% | 90.50% |
| 115 | Grok 4 Fast | 69.13% | 77.03% | 86.15% |
| 116 | Mistral Small 3.2 24B | 68.93% | 71.87% | 78.58% |
| 117 | Hermes 3 405B | 68.75% | 80.92% | 82.86% |
| 118 | Grok 4 | 68.65% | 77.34% | 88.12% |
| 119 | DeepSeek V3.1 | 68.61% | 77.45% | 82.39% |
| 120 | Gemini 3.5 Flash (Reasoning) | 67.65% | 79.87% | 94.08% |
| 121 | Nemotron 3 Super | 67.38% | 69.75% | 84.56% |
| 122 | Mistral NeMO | 67.00% | 76.72% | 65.04% |
| 123 | Gemini 3 Pro (Preview) | 67.00% | 77.77% | 88.79% |
| 124 | DeepSeek-V2 Chat | 66.95% | 77.20% | 84.83% |
| 125 | Gemini 2.5 Flash Lite (Reasoning) | 65.73% | 71.64% | 85.75% |
| 126 | Z.AI GLM 4.5 Air | 65.43% | 74.61% | 83.12% |
| 127 | Gemini 2.5 Flash (Reasoning) | 65.33% | 76.30% | 86.51% |
| 128 | Arcee AI: Trinity Large (Preview) | 65.33% | 75.26% | 73.33% |
| 129 | GPT-4o, May 13th (temp=0) | 64.81% | 74.89% | 85.36% |
| 130 | Gemini 3 Flash (Preview) | 64.78% | 75.04% | 85.35% |
| 131 | Gemma 3 27B | 64.44% | 78.79% | 77.85% |
| 132 | Qwen 2.5 72B | 64.34% | 75.16% | 75.46% |
| 133 | Cohere Command R+ (Aug. 2024) | 64.24% | 77.70% | 69.03% |
| 134 | Gemini 3.5 Flash (Reasoning, Minimal) | 63.97% | 78.55% | 86.47% |
| 135 | Arcee AI: Trinity Mini | 63.42% | 74.01% | 70.90% |
| 136 | GPT-4o, Aug. 6th (temp=0) | 63.20% | 73.65% | 82.45% |
| 137 | Cydonia 24B V4.1 | 62.72% | 74.19% | 75.09% |
| 138 | Gemini 2.5 Flash Lite | 62.67% | 75.05% | 81.08% |
| 139 | GPT-5 Nano | 62.32% | 67.04% | 82.60% |
| 140 | Llama 3.1 Nemotron 70B | 62.12% | 71.71% | 74.70% |
| 141 | Qwen 3.5 Plus (2026-02-15) | 61.06% | 77.07% | 85.96% |
| 142 | Nemotron 3 Nano | 60.70% | 65.87% | 77.73% |
| 143 | Claude 3 Haiku | 60.58% | 74.53% | 71.19% |
| 144 | Inception Mercury 2 | 59.94% | 68.31% | 83.85% |
| 145 | GPT-4o, Aug. 6th (temp=1) | 59.42% | 75.50% | 82.62% |
| 146 | Hermes 3 70B | 59.25% | 77.41% | 72.57% |
| 147 | Stealth: Aurora Alpha | 59.16% | 67.54% | 83.79% |
| 148 | GPT-4o, May 13th (temp=1) | 58.51% | 75.88% | 83.80% |
| 149 | GPT-4.1 Mini | 57.72% | 74.52% | 83.20% |
| 150 | GPT-4o Mini (temp=0) | 56.91% | 73.10% | 78.29% |
| 151 | GPT-OSS 120B | 55.74% | 67.85% | 86.44% |
| 152 | GPT-4.1 Nano | 55.61% | 71.81% | 71.94% |
| 153 | Gemma 3 12B | 54.87% | 75.38% | 78.41% |
| 154 | GPT-4o Mini (temp=1) | 53.50% | 74.37% | 79.08% |
| 155 | Gemma 3 4B | 52.95% | 72.10% | 68.57% |