Reasoning
20 scenarios across 2 subcategories. 155 models scored.
Subcategories
| Subcategory | Avg Score | Best Model | Best Score |
|---|---|---|---|
| Deduction | 90.63% | Gemini 3.5 Flash (Reasoning) | 99.50% |
| Attention | 85.94% | Claude Opus 4.5 | 98.41% |
Model Leaderboard
All models ranked by their Reasoning category score.
| # | Model | Reasoning | Deduction | Attention | Overall |
|---|---|---|---|---|---|
| 1 | Gemini 3.5 Flash (Reasoning) | 98.45% | 99.50% | 97.41% | 94.08% |
| 2 | Gemini 3 Flash (Preview, Reasoning) | 98.05% | 99.50% | 96.60% | 90.50% |
| 3 | Gemma 4 31B (Reasoning) | 97.19% | 98.50% | 95.88% | 91.71% |
| 4 | Gemini 2.5 Pro | 96.91% | 97.00% | 96.82% | 88.53% |
| 5 | Z.AI GLM 5.1 | 96.83% | 96.50% | 97.16% | 94.37% |
| 6 | Gemma 4 31B | 96.52% | 98.00% | 95.04% | 86.91% |
| 7 | Qwen3.6 Max Preview | 96.51% | 96.00% | 97.02% | 94.54% |
| 8 | Gemini 3.1 Pro (Preview) | 96.01% | 96.00% | 96.03% | 94.37% |
| 9 | Grok 4 | 96.01% | 95.00% | 97.02% | 88.12% |
| 10 | Z.AI GLM 5 | 95.89% | 96.00% | 95.78% | 91.23% |
| 11 | Qwen3.7 Max | 95.84% | 95.00% | 96.68% | 95.75% |
| 12 | Claude Opus 4.7 | 95.72% | 97.50% | 93.95% | 89.93% |
| 13 | Z.AI GLM 5 Turbo | 95.67% | 95.00% | 96.34% | 94.27% |
| 14 | GPT-5 | 95.67% | 95.00% | 96.33% | 91.93% |
| 15 | ByteDance Seed 2.0 Lite | 95.50% | 96.50% | 94.49% | 84.80% |
| 16 | Grok 4.3 (Reasoning) | 95.46% | 95.00% | 95.92% | 93.60% |
| 17 | Claude Opus 4.7 (Reasoning) | 95.44% | 95.00% | 95.87% | 93.23% |
| 18 | MoonshotAI: Kimi K2.5 | 95.41% | 96.00% | 94.83% | 91.04% |
| 19 | Gemini 3 Pro (Preview) | 95.24% | 95.00% | 95.47% | 88.79% |
| 20 | MoonshotAI: Kimi K2.6 | 95.22% | 95.00% | 95.44% | 92.31% |
| 21 | Gemma 4 26B (Reasoning) | 95.21% | 99.00% | 91.42% | 91.49% |
| 22 | GPT-5.5 | 95.16% | 95.00% | 95.33% | 89.09% |
| 23 | GPT-5.1 | 95.14% | 95.00% | 95.29% | 92.54% |
| 24 | Z.AI GLM 4.6 | 95.12% | 97.50% | 92.74% | 89.11% |
| 25 | DeepSeek V4 Flash (Reasoning) | 95.08% | 94.44% | 95.71% | 89.01% |
| 26 | Qwen 3.5 397B A17B | 95.06% | 95.00% | 95.13% | 91.73% |
| 27 | o4 Mini High | 95.02% | 95.00% | 95.05% | 90.29% |
| 28 | GPT-5.5 (Reasoning, Low) | 95.01% | 95.00% | 95.03% | 92.59% |
| 29 | Z.AI GLM 4.7 | 94.99% | 95.00% | 94.98% | 88.69% |
| 30 | Qwen 3.5 Plus (2026-04-20) | 94.99% | 94.44% | 95.53% | 91.51% |
| 31 | Qwen 3.5 122B | 94.93% | 95.00% | 94.87% | 91.53% |
| 32 | Grok 4 Fast | 94.89% | 95.00% | 94.78% | 86.15% |
| 33 | GPT-5.5 (Reasoning) | 94.89% | 95.00% | 94.78% | 92.98% |
| 34 | Qwen 3.5 35B | 94.88% | 95.00% | 94.75% | 88.00% |
| 35 | Gemini 3 Flash (Preview) | 94.79% | 95.00% | 94.58% | 85.35% |
| 36 | GPT-5.4 (Reasoning) | 94.78% | 95.00% | 94.55% | 93.24% |
| 37 | Qwen 3.5 Flash | 94.66% | 95.00% | 94.31% | 86.38% |
| 38 | DeepSeek V4 Pro (Reasoning) | 94.61% | 94.44% | 94.77% | 90.10% |
| 39 | GPT-5.4 Mini (Reasoning) | 94.56% | 95.00% | 94.13% | 90.65% |
| 40 | GPT-5.2 | 94.54% | 95.50% | 93.58% | 90.26% |
| 41 | Claude Sonnet 4 | 94.48% | 94.44% | 94.52% | 88.72% |
| 42 | o4 Mini | 94.45% | 95.50% | 93.40% | 88.35% |
| 43 | GPT-5 Mini | 94.36% | 95.50% | 93.22% | 92.62% |
| 44 | GPT-5.4 (Reasoning, Low) | 94.34% | 95.00% | 93.67% | 91.41% |
| 45 | Qwen 3.6 Flash | 94.20% | 95.00% | 93.41% | 90.65% |
| 46 | Aion 2.0 | 94.13% | 92.78% | 95.49% | 89.21% |
| 47 | Gemini 3.5 Flash (Reasoning, Minimal) | 94.12% | 92.83% | 95.40% | 86.47% |
| 48 | Qwen 3.6 35B | 94.08% | 95.00% | 93.16% | 89.05% |
| 49 | Claude Opus 4.5 | 93.93% | 89.44% | 98.41% | 89.69% |
| 50 | GPT-5.4 | 93.92% | 95.00% | 92.85% | 84.32% |
| 51 | Gemini 2.5 Flash Lite (Reasoning) | 93.86% | 96.50% | 91.22% | 85.75% |
| 52 | Gemini 2.5 Flash (Reasoning) | 93.81% | 95.89% | 91.73% | 86.51% |
| 53 | Claude Opus 4.6 (Reasoning) | 93.77% | 89.44% | 98.10% | 95.02% |
| 54 | Grok 4.1 Fast | 93.58% | 91.11% | 96.05% | 89.55% |
| 55 | Claude Opus 4.8 (Reasoning) | 93.53% | 89.44% | 97.61% | 92.22% |
| 56 | Qwen 3.5 Plus (2026-02-15) | 93.45% | 93.94% | 92.96% | 85.96% |
| 57 | Claude Opus 4.8 (Reasoning, Low) | 93.37% | 89.44% | 97.30% | 92.14% |
| 58 | Claude Opus 4.6 | 93.33% | 88.89% | 97.78% | 92.35% |
| 59 | MiniMax M2.7 | 93.28% | 94.94% | 91.61% | 89.10% |
| 60 | Nemotron 3 Super | 93.11% | 95.00% | 91.22% | 84.56% |
| 61 | Qwen 3.6 27B | 93.08% | 93.94% | 92.21% | 89.72% |
| 62 | Qwen 3.5 9B | 92.93% | 95.00% | 90.87% | 86.05% |
| 63 | Claude Sonnet 4.6 (Reasoning) | 92.76% | 89.44% | 96.08% | 93.66% |
| 64 | Qwen 3.5 27B | 92.73% | 95.00% | 90.46% | 90.85% |
| 65 | Gemini 2.5 Flash | 92.60% | 95.00% | 90.21% | 80.60% |
| 66 | Claude Opus 4 | 92.59% | 91.94% | 93.24% | 87.69% |
| 67 | Claude Sonnet 4.5 | 92.50% | 89.44% | 95.56% | 88.03% |
| 68 | Xiaomi MIMO v2.5 | 92.43% | 90.56% | 94.31% | 85.05% |
| 69 | GPT-OSS 120B | 92.42% | 95.00% | 89.84% | 86.44% |
| 70 | MiniMax M2.5 | 92.42% | 95.50% | 89.33% | 88.71% |
| 71 | ByteDance Seed 2.0 Mini | 92.40% | 91.11% | 93.68% | 86.91% |
| 72 | GPT-5.4 Mini (Reasoning, Low) | 92.28% | 95.00% | 89.57% | 85.75% |
| 73 | Gemini 3.1 Flash Lite (Preview) | 92.15% | 94.44% | 89.85% | 85.87% |
| 74 | Gemini 3.1 Flash Lite | 92.10% | 95.00% | 89.19% | 85.75% |
| 75 | Xiaomi MIMO v2.5 Pro | 92.07% | 89.44% | 94.70% | 87.36% |
| 76 | Inception Mercury 2 | 92.03% | 95.00% | 89.05% | 83.85% |
| 77 | MiniMax M3 | 91.84% | 87.78% | 95.91% | 90.88% |
| 78 | Gemini 3.1 Flash Lite (Reasoning) | 91.72% | 94.44% | 89.00% | 86.41% |
| 79 | Stealth: Healer Alpha | 91.67% | 90.00% | 93.35% | 85.93% |
| 80 | Stealth: Hunter Alpha | 91.67% | 89.94% | 93.39% | 87.34% |
| 81 | ByteDance Seed 1.6 | 91.49% | 90.00% | 92.98% | 90.70% |
| 82 | Z.AI GLM 4.5 | 91.03% | 92.22% | 89.84% | 86.27% |
| 83 | Claude 3.5 Sonnet | 90.30% | 89.44% | 91.16% | 84.24% |
| 84 | Stealth: Aurora Alpha | 90.11% | 95.00% | 85.21% | 83.79% |
| 85 | Claude 3.7 Sonnet | 89.94% | 89.44% | 90.43% | 83.39% |
| 86 | Nemotron 3 Nano | 89.91% | 95.00% | 84.82% | 77.73% |
| 87 | GPT-5 Nano | 89.61% | 95.00% | 84.22% | 82.60% |
| 88 | Z.AI GLM 4.7 Flash | 89.50% | 95.00% | 83.99% | 84.82% |
| 89 | DeepSeek V3.2 | 89.46% | 90.06% | 88.87% | 82.25% |
| 90 | Mistral Medium 3.1 | 89.32% | 89.44% | 89.19% | 77.83% |
| 91 | Mistral Large 3 | 88.95% | 89.44% | 88.45% | 85.43% |
| 92 | DeepSeek V3 (2024-12-26) | 88.71% | 90.39% | 87.02% | 83.68% |
| 93 | DeepSeek-V2 Chat | 88.70% | 89.44% | 87.95% | 84.83% |
| 94 | GPT-4o, May 13th (temp=0) | 88.58% | 89.44% | 87.71% | 85.36% |
| 95 | GPT-5.4 Nano (Reasoning) | 88.48% | 93.89% | 83.07% | 81.36% |
| 96 | Claude Sonnet 4.6 | 88.48% | 83.89% | 93.07% | 91.15% |
| 97 | GPT-4.1 | 88.46% | 89.94% | 86.98% | 88.68% |
| 98 | DeepSeek V3 (2025-03-24) | 88.45% | 89.61% | 87.29% | 81.99% |
| 99 | Mistral Large 2 | 88.20% | 87.78% | 88.62% | 82.41% |
| 100 | GPT-5.4 Mini | 88.04% | 96.00% | 80.08% | 82.43% |
| 101 | Gemma 4 26B | 88.02% | 97.00% | 79.04% | 85.84% |
| 102 | Mistral Small Creative | 87.99% | 92.94% | 83.04% | 73.27% |
| 103 | Z.AI GLM 4.5 Air | 87.91% | 88.83% | 86.99% | 83.12% |
| 104 | Mistral Small 4 (Reasoning) | 87.78% | 90.44% | 85.12% | 82.39% |
| 105 | Claude Haiku 4.5 | 87.76% | 89.44% | 86.08% | 85.14% |
| 106 | GPT-4o, Aug. 6th (temp=0) | 87.59% | 89.44% | 85.73% | 82.45% |
| 107 | DeepSeek V4 Pro | 87.07% | 84.17% | 89.98% | 82.63% |
| 108 | Grok 4.20 (Beta) | 87.05% | 86.72% | 87.37% | 83.85% |
| 109 | GPT-4o, Aug. 6th (temp=1) | 86.91% | 89.44% | 84.37% | 82.62% |
| 110 | Gemma 3 27B | 86.74% | 95.00% | 78.48% | 77.85% |
| 111 | Writer: Palmyra X5 | 86.57% | 89.44% | 83.69% | 79.57% |
| 112 | ByteDance Seed 1.6 Flash | 86.52% | 91.67% | 81.38% | 73.27% |
| 113 | Qwen 3 32B | 86.35% | 88.89% | 83.81% | 82.21% |
| 114 | GPT-4o, May 13th (temp=1) | 85.98% | 89.44% | 82.52% | 83.80% |
| 115 | Inception Mercury | 85.96% | 95.00% | 76.92% | 79.50% |
| 116 | GPT-4.1 Mini | 85.83% | 89.44% | 82.22% | 83.20% |
| 117 | Qwen3 235B A22B Instruct 2507 | 85.82% | 88.39% | 83.25% | 80.10% |
| 118 | Gemini 2.5 Flash Lite | 85.80% | 95.00% | 76.60% | 81.08% |
| 119 | Hermes 3 405B | 85.58% | 88.28% | 82.88% | 82.86% |
| 120 | Grok 4.20 | 84.81% | 81.50% | 88.11% | 81.70% |
| 121 | Grok 4.3 | 84.62% | 85.89% | 83.35% | 78.66% |
| 122 | DeepSeek V3.1 | 83.95% | 84.94% | 82.96% | 82.39% |
| 123 | Qwen 2.5 72B | 83.43% | 89.44% | 77.42% | 75.46% |
| 124 | Ministral 3 14B | 83.24% | 89.44% | 77.03% | 72.54% |
| 125 | Grok 4.20 (Beta, Reasoning) | 82.64% | 68.33% | 96.94% | 91.49% |
| 126 | Llama 3.1 Nemotron 70B | 82.19% | 87.22% | 77.15% | 74.70% |
| 127 | Mistral Small 3.2 24B | 81.71% | 83.89% | 79.53% | 78.58% |
| 128 | GPT-4o Mini (temp=0) | 81.26% | 94.44% | 68.07% | 78.29% |
| 129 | GPT-4o Mini (temp=1) | 80.28% | 93.44% | 67.12% | 79.08% |
| 130 | Gemma 3 12B | 79.42% | 95.00% | 63.84% | 78.41% |
| 131 | Llama 3.1 70B | 79.31% | 85.00% | 73.63% | 78.40% |
| 132 | DeepSeek V4 Flash | 79.16% | 68.94% | 89.38% | 82.02% |
| 133 | Grok 4.20 (Reasoning) | 79.11% | 61.11% | 97.12% | 91.39% |
| 134 | Hermes 3 70B | 79.08% | 89.39% | 68.76% | 72.57% |
| 135 | GPT-5.4 Nano (Reasoning, Low) | 78.93% | 95.00% | 62.85% | 79.48% |
| 136 | Mistral Small 4 | 78.72% | 89.50% | 67.95% | 76.46% |
| 137 | Claude 3 Haiku | 77.94% | 88.89% | 66.98% | 71.19% |
| 138 | Arcee AI: Trinity Large (Preview) | 77.24% | 83.89% | 70.59% | 73.33% |
| 139 | Arcee AI: Trinity Mini | 76.94% | 82.28% | 71.60% | 70.90% |
| 140 | Cydonia 24B V4.1 | 76.47% | 83.61% | 69.33% | 75.09% |
| 141 | Mistral Large | 76.31% | 66.06% | 86.57% | 80.15% |
| 142 | GPT-5.4 Nano | 75.66% | 93.06% | 58.27% | 74.40% |
| 143 | Ministral 8B | 73.78% | 76.00% | 71.56% | 64.87% |
| 144 | Gemma 3 4B | 73.64% | 95.00% | 52.28% | 68.57% |
| 145 | Ministral 3 3B | 71.88% | 77.78% | 65.98% | 67.22% |
| 146 | Ministral 3 8B | 71.64% | 68.33% | 74.95% | 71.76% |
| 147 | GPT-4.1 Nano | 70.24% | 94.44% | 46.04% | 71.94% |
| 148 | Ministral 3B | 69.70% | 72.83% | 66.56% | 61.29% |
| 149 | Llama 3.1 8B | 69.12% | 86.78% | 51.46% | 63.35% |
| 150 | WizardLM 2 8x22b | 67.36% | 69.94% | 64.77% | 71.06% |
| 151 | Cohere Command R+ (Aug. 2024) | 65.10% | 63.83% | 66.37% | 69.03% |
| 152 | Skyfall 36B V2 | 62.23% | 70.94% | 53.52% | 65.76% |
| 153 | Mistral NeMO | 57.59% | 87.33% | 27.84% | 65.04% |
| 154 | LFM2 24B | 54.88% | 78.89% | 30.88% | 58.77% |
| 155 | Rocinante 12B | 54.31% | 74.89% | 33.73% | 54.54% |