Structural Counting
Subcategory of Utility. 155 models scored.
Model Leaderboard
All models ranked by their Structural Counting subcategory score.
| # | Model | Structural Counting | Utility | Overall |
|---|---|---|---|---|
| 1 | Qwen3.7 Max | 100.00% | 99.54% | 95.75% |
| 2 | Claude Opus 4.6 (Reasoning) | 100.00% | 98.93% | 95.02% |
| 3 | Qwen3.6 Max Preview | 100.00% | 98.34% | 94.54% |
| 4 | Gemini 3.1 Pro (Preview) | 100.00% | 99.91% | 94.37% |
| 5 | GPT-5.4 (Reasoning) | 100.00% | 96.89% | 93.24% |
| 6 | Claude Opus 4.7 (Reasoning) | 100.00% | 97.87% | 93.23% |
| 7 | GPT-5.5 (Reasoning) | 100.00% | 96.60% | 92.98% |
| 8 | GPT-5.5 (Reasoning, Low) | 100.00% | 96.36% | 92.59% |
| 9 | MoonshotAI: Kimi K2.6 | 100.00% | 97.42% | 92.31% |
| 10 | Claude Opus 4.8 (Reasoning) | 100.00% | 99.26% | 92.22% |
| 11 | Qwen 3.5 397B A17B | 100.00% | 97.50% | 91.73% |
| 12 | Qwen 3.5 122B | 100.00% | 96.36% | 91.53% |
| 13 | Grok 4.20 (Beta, Reasoning) | 100.00% | 95.41% | 91.49% |
| 14 | GPT-5.4 (Reasoning, Low) | 100.00% | 95.32% | 91.41% |
| 15 | MoonshotAI: Kimi K2.5 | 100.00% | 96.63% | 91.04% |
| 16 | Qwen 3.5 27B | 100.00% | 95.67% | 90.85% |
| 17 | Gemini 3 Flash (Preview, Reasoning) | 100.00% | 97.20% | 90.50% |
| 18 | Aion 2.0 | 100.00% | 90.91% | 89.21% |
| 19 | Qwen 3.6 35B | 100.00% | 96.20% | 89.05% |
| 20 | Gemini 3 Pro (Preview) | 100.00% | 96.14% | 88.79% |
| 21 | Gemini 2.5 Pro | 100.00% | 92.18% | 88.53% |
| 22 | Qwen 3.5 35B | 100.00% | 96.42% | 88.00% |
| 23 | Qwen 3.5 Flash | 100.00% | 96.11% | 86.38% |
| 24 | Claude Sonnet 4.6 (Reasoning) | 99.00% | 97.88% | 93.66% |
| 25 | Qwen 3.6 Flash | 98.00% | 96.09% | 90.65% |
| 26 | Z.AI GLM 4.6 | 98.00% | 88.58% | 89.11% |
| 27 | Gemini 3.5 Flash (Reasoning) | 97.50% | 98.86% | 94.08% |
| 28 | Gemma 4 31B (Reasoning) | 97.50% | 96.32% | 91.71% |
| 29 | Qwen 3.5 Plus (2026-04-20) | 97.50% | 96.42% | 91.51% |
| 30 | o4 Mini High | 97.50% | 98.67% | 90.29% |
| 31 | GPT-5.2 | 97.00% | 96.22% | 90.26% |
| 32 | Gemini 2.5 Flash Lite (Reasoning) | 96.50% | 89.63% | 85.75% |
| 33 | Z.AI GLM 5 Turbo | 96.00% | 96.36% | 94.27% |
| 34 | Qwen 3.6 27B | 95.50% | 94.32% | 89.72% |
| 35 | Qwen 3.5 9B | 95.50% | 94.02% | 86.05% |
| 36 | Z.AI GLM 5.1 | 95.00% | 97.51% | 94.37% |
| 37 | Gemma 4 26B (Reasoning) | 95.00% | 95.69% | 91.49% |
| 38 | Z.AI GLM 5 | 95.00% | 94.11% | 91.23% |
| 39 | DeepSeek V4 Flash (Reasoning) | 95.00% | 87.53% | 89.01% |
| 40 | Qwen3 235B A22B Instruct 2507 | 95.00% | 83.15% | 80.10% |
| 41 | Llama 3.1 Nemotron 70B | 94.50% | 88.31% | 74.70% |
| 42 | GPT-5 Mini | 94.00% | 98.39% | 92.62% |
| 43 | Claude Opus 4.8 (Reasoning, Low) | 94.00% | 98.00% | 92.14% |
| 44 | MiniMax M3 | 93.00% | 93.59% | 90.88% |
| 45 | Z.AI GLM 4.7 | 93.00% | 94.31% | 88.69% |
| 46 | o4 Mini | 92.50% | 96.31% | 88.35% |
| 47 | Claude Opus 4.7 | 92.00% | 95.77% | 89.93% |
| 48 | GPT-5.1 | 91.50% | 95.33% | 92.54% |
| 49 | DeepSeek V4 Pro (Reasoning) | 91.50% | 93.24% | 90.10% |
| 50 | GPT-5.4 Nano (Reasoning) | 91.00% | 93.34% | 81.36% |
| 51 | GPT-5.4 Mini (Reasoning) | 90.50% | 94.44% | 90.65% |
| 52 | MiniMax M2.5 | 90.50% | 90.42% | 88.71% |
| 53 | GPT-5.4 Nano (Reasoning, Low) | 90.50% | 91.42% | 79.48% |
| 54 | Gemini 2.5 Flash (Reasoning) | 90.00% | 82.25% | 86.51% |
| 55 | ByteDance Seed 1.6 Flash | 90.00% | 84.16% | 73.27% |
| 56 | Claude Opus 4 | 89.50% | 88.81% | 87.69% |
| 57 | Qwen 3.5 Plus (2026-02-15) | 89.00% | 86.65% | 85.96% |
| 58 | MiniMax M2.7 | 88.00% | 95.50% | 89.10% |
| 59 | Grok 4.20 (Reasoning) | 87.50% | 92.61% | 91.39% |
| 60 | ByteDance Seed 2.0 Lite | 87.50% | 92.23% | 84.80% |
| 61 | GPT-4.1 | 85.50% | 90.57% | 88.68% |
| 62 | ByteDance Seed 2.0 Mini | 85.50% | 91.88% | 86.91% |
| 63 | Nemotron 3 Super | 85.00% | 95.29% | 84.56% |
| 64 | Grok 4 | 85.00% | 89.67% | 88.12% |
| 65 | GPT-5 Nano | 85.00% | 93.91% | 82.60% |
| 66 | Stealth: Hunter Alpha | 83.00% | 84.63% | 87.34% |
| 67 | Z.AI GLM 4.5 | 83.00% | 79.19% | 86.27% |
| 68 | Writer: Palmyra X5 | 83.00% | 79.71% | 79.57% |
| 69 | Gemini 3.1 Flash Lite (Preview) | 82.00% | 94.00% | 85.87% |
| 70 | Claude Sonnet 4 | 82.00% | 84.02% | 88.72% |
| 71 | Gemini 3.1 Flash Lite (Reasoning) | 81.50% | 92.32% | 86.41% |
| 72 | Gemini 3.1 Flash Lite | 81.50% | 92.77% | 85.75% |
| 73 | Z.AI GLM 4.7 Flash | 81.00% | 88.98% | 84.82% |
| 74 | Qwen 3 32B | 80.50% | 81.66% | 82.21% |
| 75 | ByteDance Seed 1.6 | 80.00% | 90.83% | 90.70% |
| 76 | DeepSeek-V2 Chat | 79.50% | 83.82% | 84.83% |
| 77 | GPT-4o, May 13th (temp=0) | 78.00% | 83.13% | 85.36% |
| 78 | Xiaomi MIMO v2.5 Pro | 77.00% | 82.62% | 87.36% |
| 79 | Stealth: Aurora Alpha | 77.00% | 92.59% | 83.79% |
| 80 | GPT-5 | 76.50% | 93.53% | 91.93% |
| 81 | Claude Sonnet 4.6 | 76.00% | 88.52% | 91.15% |
| 82 | Mistral Small 4 (Reasoning) | 76.00% | 85.61% | 82.39% |
| 83 | GPT-OSS 120B | 75.50% | 92.03% | 86.44% |
| 84 | Gemini 2.5 Flash Lite | 74.00% | 80.14% | 81.08% |
| 85 | Inception Mercury 2 | 73.50% | 92.86% | 83.85% |
| 86 | Grok 4.3 (Reasoning) | 73.50% | 92.94% | 93.60% |
| 87 | Claude Opus 4.5 | 72.50% | 89.84% | 89.69% |
| 88 | Mistral Large 3 | 72.00% | 84.91% | 85.43% |
| 89 | Xiaomi MIMO v2.5 | 71.50% | 81.15% | 85.05% |
| 90 | Stealth: Healer Alpha | 71.00% | 82.30% | 85.93% |
| 91 | Claude Haiku 4.5 | 70.50% | 72.48% | 85.14% |
| 92 | Claude Opus 4.6 | 70.00% | 90.72% | 92.35% |
| 93 | DeepSeek V3.2 | 70.00% | 81.58% | 82.25% |
| 94 | Mistral Large | 69.50% | 73.04% | 80.15% |
| 95 | Gemma 3 12B | 69.50% | 79.28% | 78.41% |
| 96 | Gemma 4 31B | 69.00% | 86.69% | 86.91% |
| 97 | Claude Sonnet 4.5 | 68.00% | 83.78% | 88.03% |
| 98 | Llama 3.1 70B | 68.00% | 81.03% | 78.40% |
| 99 | GPT-5.4 Mini (Reasoning, Low) | 67.50% | 88.49% | 85.75% |
| 100 | Gemini 3.5 Flash (Reasoning, Minimal) | 67.00% | 83.90% | 86.47% |
| 101 | Mistral Large 2 | 66.00% | 69.19% | 82.41% |
| 102 | GPT-4.1 Mini | 65.50% | 82.30% | 83.20% |
| 103 | Grok 4.1 Fast | 64.50% | 84.12% | 89.55% |
| 104 | Z.AI GLM 4.5 Air | 64.50% | 76.57% | 83.12% |
| 105 | Qwen 2.5 72B | 64.00% | 76.43% | 75.46% |
| 106 | GPT-4o, May 13th (temp=1) | 63.50% | 80.69% | 83.80% |
| 107 | DeepSeek V3 (2024-12-26) | 62.50% | 81.87% | 83.68% |
| 108 | DeepSeek V4 Flash | 62.00% | 83.26% | 82.02% |
| 109 | Grok 4.20 (Beta) | 60.50% | 82.15% | 83.85% |
| 110 | GPT-4o, Aug. 6th (temp=1) | 60.50% | 82.44% | 82.62% |
| 111 | Inception Mercury | 60.00% | 87.38% | 79.50% |
| 112 | Gemma 4 26B | 60.00% | 83.17% | 85.84% |
| 113 | Ministral 3 8B | 60.00% | 74.43% | 71.76% |
| 114 | GPT-4o, Aug. 6th (temp=0) | 59.50% | 82.11% | 82.45% |
| 115 | DeepSeek V3.1 | 59.50% | 76.65% | 82.39% |
| 116 | Mistral Small 4 | 59.50% | 78.28% | 76.46% |
| 117 | Grok 4.20 | 58.50% | 84.11% | 81.70% |
| 118 | Ministral 3 14B | 55.50% | 79.03% | 72.54% |
| 119 | Mistral NeMO | 54.50% | 51.55% | 65.04% |
| 120 | Gemini 2.5 Flash | 54.00% | 61.45% | 80.60% |
| 121 | WizardLM 2 8x22b | 53.50% | 67.14% | 71.06% |
| 122 | DeepSeek V3 (2025-03-24) | 53.50% | 80.62% | 81.99% |
| 123 | GPT-4o Mini (temp=1) | 53.00% | 82.16% | 79.08% |
| 124 | DeepSeek V4 Pro | 52.50% | 77.57% | 82.63% |
| 125 | Hermes 3 70B | 52.50% | 61.15% | 72.57% |
| 126 | GPT-4.1 Nano | 52.50% | 68.45% | 71.94% |
| 127 | GPT-5.4 Nano | 51.50% | 78.57% | 74.40% |
| 128 | Mistral Small Creative | 51.00% | 76.28% | 73.27% |
| 129 | Nemotron 3 Nano | 50.50% | 86.00% | 77.73% |
| 130 | Ministral 3 3B | 50.00% | 72.38% | 67.22% |
| 131 | Arcee AI: Trinity Mini | 49.50% | 59.94% | 70.90% |
| 132 | Gemini 3 Flash (Preview) | 48.00% | 86.39% | 85.35% |
| 133 | Ministral 3B | 47.50% | 49.17% | 61.29% |
| 134 | Claude 3.7 Sonnet | 47.00% | 62.54% | 83.39% |
| 135 | Cydonia 24B V4.1 | 46.50% | 69.32% | 75.09% |
| 136 | Skyfall 36B V2 | 46.50% | 52.53% | 65.76% |
| 137 | Llama 3.1 8B | 46.50% | 74.82% | 63.35% |
| 138 | GPT-5.4 | 45.50% | 81.95% | 84.32% |
| 139 | GPT-4o Mini (temp=0) | 45.00% | 81.43% | 78.29% |
| 140 | Arcee AI: Trinity Large (Preview) | 44.50% | 60.74% | 73.33% |
| 141 | Claude 3 Haiku | 44.50% | 68.47% | 71.19% |
| 142 | Rocinante 12B | 43.50% | 48.47% | 54.54% |
| 143 | Gemma 3 27B | 43.00% | 76.82% | 77.85% |
| 144 | Cohere Command R+ (Aug. 2024) | 42.00% | 59.51% | 69.03% |
| 145 | Mistral Medium 3.1 | 39.00% | 80.13% | 77.83% |
| 146 | LFM2 24B | 38.50% | 69.48% | 58.77% |
| 147 | GPT-5.5 | 37.50% | 81.88% | 89.09% |
| 148 | Claude 3.5 Sonnet | 37.00% | 76.75% | 84.24% |
| 149 | Hermes 3 405B | 37.00% | 69.02% | 82.86% |
| 150 | Ministral 8B | 33.50% | 46.82% | 64.87% |
| 151 | Grok 4 Fast | 32.50% | 76.76% | 86.15% |
| 152 | GPT-5.4 Mini | 32.50% | 79.37% | 82.43% |
| 153 | Gemma 3 4B | 31.00% | 60.30% | 68.57% |
| 154 | Grok 4.3 | 27.50% | 66.41% | 78.66% |
| 155 | Mistral Small 3.2 24B | 23.50% | 73.17% | 78.58% |