Hallucination
30 scenarios across 3 subcategories. 202 models scored.
Subcategories
| Subcategory | Avg Score | Best Model | Best Score |
|---|---|---|---|
| False Positives | 78.49% | Claude Haiku 5.5 (Adaptive) | 99.06% |
| Content Invention | 97.77% | Qwen 3.8 Max (Reasoning, XHigh) | 100.00% |
| Output Corruption | 99.70% | Claude Opus 5.5 (Reasoning) | 100.00% |
Model Leaderboard
All models ranked by their Hallucination category score.
| # | Model | Hallucination | False Positives | Content Invention | Output Corruption | Overall |
|---|---|---|---|---|---|---|
| 1 | o4 Mini High | 99.53% | 98.59% | 100.00% | 100.00% | 88.78% |
| 2 | Z.AI GLM 5.3 Flash (Reasoning, Low) | 99.36% | 98.13% | 100.00% | 99.94% | 88.76% |
| 3 | Z.AI GLM 5 Turbo | 99.32% | 97.97% | 100.00% | 99.99% | 93.29% |
| 4 | Claude Opus 4.6 (Reasoning) | 99.06% | 97.19% | 100.00% | 100.00% | 95.06% |
| 5 | Grok 4.5 (Reasoning, High) | 99.06% | 97.19% | 100.00% | 100.00% | 94.12% |
| 6 | Grok 4.5 (Reasoning, Low) | 99.01% | 97.03% | 100.00% | 100.00% | 90.94% |
| 7 | Z.AI GLM 5.2 (Reasoning, High) | 98.99% | 96.98% | 100.00% | 99.98% | 93.41% |
| 8 | Z.AI GLM 5.1 | 98.84% | 96.51% | 100.00% | 100.00% | 93.74% |
| 9 | Gemma 4 26B (Reasoning) | 98.79% | 96.41% | 100.00% | 99.95% | 89.02% |
| 10 | GPT-5.4 Mini (Reasoning, Low) | 98.78% | 96.36% | 100.00% | 99.98% | 83.57% |
| 11 | Claude Opus 4.7 (Reasoning) | 98.69% | 96.09% | 100.00% | 99.98% | 92.53% |
| 12 | Gemini 4 Argon (Reasoning, Medium) | 98.69% | 96.25% | 100.00% | 99.81% | 93.81% |
| 13 | GPT-5.6 Luna (Reasoning, Medium) | 98.65% | 95.94% | 100.00% | 100.00% | 90.61% |
| 14 | Muse Spark 1.3 (Reasoning, Medium) | 98.57% | 95.73% | 100.00% | 100.00% | 94.06% |
| 15 | o4 Mini | 98.54% | 95.63% | 100.00% | 100.00% | 86.56% |
| 16 | Qwen 3.5 Plus (2026-04-20) | 98.38% | 96.25% | 100.00% | 98.89% | 89.79% |
| 17 | GPT-5 Mini | 98.28% | 94.85% | 100.00% | 100.00% | 91.31% |
| 18 | Grok 4.6 (Reasoning, High) | 98.25% | 94.84% | 100.00% | 99.91% | 92.76% |
| 19 | GPT-5.4 Mini (Reasoning) | 98.11% | 94.32% | 100.00% | 100.00% | 89.82% |
| 20 | Z.AI GLM 5 | 98.04% | 94.11% | 100.00% | 100.00% | 89.60% |
| 21 | Gemini 3.7 Flash (Reasoning, Medium) | 97.97% | 93.91% | 100.00% | 100.00% | 94.85% |
| 22 | Muse Spark 1.2 (Reasoning, Medium) | 97.93% | 97.37% | 96.43% | 99.98% | 94.71% |
| 23 | Grok 4.3 (Reasoning) | 97.86% | 93.59% | 100.00% | 100.00% | 90.99% |
| 24 | MiniMax M3 | 97.83% | 93.49% | 100.00% | 100.00% | 90.45% |
| 25 | Gemini 2.5 Flash (Reasoning) | 97.79% | 93.44% | 100.00% | 99.94% | 84.14% |
| 26 | Xiaomi MIMO v2.6 Flash | 97.74% | 93.44% | 100.00% | 99.78% | 87.31% |
| 27 | Kimi K3 (Reasoning, Low) | 97.73% | 93.28% | 100.00% | 99.92% | 92.07% |
| 28 | Claude Opus 5.5 (Reasoning) | 97.63% | 97.66% | 95.24% | 100.00% | 96.43% |
| 29 | GPT-OSS 120B | 97.63% | 92.97% | 100.00% | 99.92% | 84.81% |
| 30 | Xiaomi MIMO v2.5 | 97.61% | 92.92% | 100.00% | 99.93% | 83.95% |
| 31 | ByteDance Seed 1.6 | 97.57% | 92.71% | 100.00% | 100.00% | 89.59% |
| 32 | GPT-5.2 | 97.55% | 92.64% | 100.00% | 100.00% | 89.45% |
| 33 | Qwen 3.6 27B | 97.42% | 92.33% | 100.00% | 99.95% | 88.33% |
| 34 | Claude Opus 4.8 (Reasoning) | 97.41% | 92.24% | 100.00% | 100.00% | 92.33% |
| 35 | Gemini 3.6 Flash (Reasoning) | 97.34% | 92.03% | 100.00% | 100.00% | 94.90% |
| 36 | Nemotron 3 Super | 97.34% | 92.03% | 100.00% | 100.00% | 81.69% |
| 37 | Claude Opus 5 (Reasoning, Low) | 97.34% | 92.03% | 100.00% | 99.97% | 92.06% |
| 38 | Claude Opus 4.8 (Reasoning, Low) | 97.33% | 91.98% | 100.00% | 100.00% | 91.89% |
| 39 | Qwen 3.7 Max | 97.15% | 91.51% | 100.00% | 99.95% | 94.55% |
| 40 | Xiaomi MIMO v2.5 Pro | 97.02% | 91.05% | 100.00% | 100.00% | 86.05% |
| 41 | Gemini 2.5 Flash Lite (Reasoning) | 96.99% | 95.78% | 95.24% | 99.96% | 83.10% |
| 42 | GPT-5.4 Nano (Reasoning) | 96.98% | 90.95% | 100.00% | 100.00% | 80.02% |
| 43 | Claude Sonnet 4.6 (Reasoning) | 96.98% | 90.94% | 100.00% | 100.00% | 93.64% |
| 44 | Kimi K3 (Reasoning, High) | 96.97% | 90.91% | 100.00% | 100.00% | 92.99% |
| 45 | DeepSeek V4 Flash (Reasoning) | 96.92% | 94.32% | 96.43% | 100.00% | 88.06% |
| 46 | Aion 3.5 Mini (Reasoning, High) | 96.91% | 90.78% | 100.00% | 99.96% | 92.36% |
| 47 | Gemini 3.8 Flash (Reasoning, Medium) | 96.88% | 90.63% | 100.00% | 100.00% | 95.72% |
| 48 | Claude Opus 5 (Reasoning) | 96.86% | 90.57% | 100.00% | 100.00% | 91.15% |
| 49 | Mistral Large 4.0 (Reasoning) | 96.85% | 90.60% | 100.00% | 99.95% | 92.14% |
| 50 | Claude Opus 4.6 | 96.80% | 90.40% | 100.00% | 100.00% | 92.31% |
| 51 | Muse Spark 1.1 (Reasoning, Medium) | 96.79% | 97.50% | 92.86% | 100.00% | 93.81% |
| 52 | Claude Sonnet 5 (Reasoning) | 96.77% | 90.31% | 100.00% | 100.00% | 90.40% |
| 53 | Ember-1 (Reasoning, Max) | 96.67% | 90.00% | 100.00% | 100.00% | 95.52% |
| 54 | Gemini 3.6 Flash (Reasoning, Minimal) | 96.53% | 89.59% | 100.00% | 100.00% | 86.68% |
| 55 | GPT-6 Luna (Reasoning, Medium) | 96.53% | 89.58% | 100.00% | 100.00% | 92.40% |
| 56 | Claude Sonnet 5 (Reasoning, Low) | 96.44% | 89.32% | 100.00% | 100.00% | 90.16% |
| 57 | Gemma 4 31B (Reasoning) | 96.37% | 89.11% | 100.00% | 100.00% | 89.64% |
| 58 | Thinking Machines Inkling (Reasoning) | 96.34% | 89.01% | 100.00% | 100.00% | 90.78% |
| 59 | Grok 4.20 (Reasoning) | 96.30% | 88.89% | 100.00% | 100.00% | 90.87% |
| 60 | GPT-6 Luna (Reasoning, High) | 96.23% | 88.70% | 100.00% | 100.00% | 93.95% |
| 61 | GPT-5.1 | 96.22% | 88.65% | 100.00% | 100.00% | 90.73% |
| 62 | Muse Glimmer 30B (Reasoning, Medium) | 96.19% | 92.14% | 96.43% | 100.00% | 88.81% |
| 63 | Aion 3.5 (Reasoning, High) | 96.13% | 88.39% | 100.00% | 100.00% | 91.90% |
| 64 | Qwen 3.6 Flash | 96.13% | 88.39% | 100.00% | 100.00% | 89.31% |
| 65 | Claude Haiku 5.5 (Adaptive) | 96.12% | 99.06% | 89.29% | 100.00% | 89.37% |
| 66 | Claude Sonnet 5.5 (Reasoning) | 96.09% | 88.28% | 100.00% | 100.00% | 92.77% |
| 67 | GPT-5 | 95.92% | 87.76% | 100.00% | 100.00% | 91.48% |
| 68 | GPT-5.6 Sol | 95.87% | 87.60% | 100.00% | 100.00% | 90.76% |
| 69 | Qwen 3.6 Max Preview | 95.86% | 87.58% | 100.00% | 100.00% | 93.72% |
| 70 | GPT-5.4 (Reasoning, Low) | 95.71% | 87.14% | 100.00% | 100.00% | 90.91% |
| 71 | GPT-5.4 Nano (Reasoning, Low) | 95.71% | 87.13% | 100.00% | 100.00% | 77.46% |
| 72 | Gemini 3.5 Flash (Reasoning) | 95.61% | 86.82% | 100.00% | 100.00% | 93.35% |
| 73 | GPT-4.1 | 95.60% | 86.82% | 100.00% | 99.97% | 86.82% |
| 74 | Aion 3.0 | 95.57% | 86.82% | 100.00% | 99.88% | 88.78% |
| 75 | Grok 4.7 (Reasoning, High) | 95.48% | 86.43% | 100.00% | 100.00% | 92.62% |
| 76 | Muse Spark 1.1 (Reasoning, Minimal) | 95.34% | 98.59% | 87.50% | 99.94% | 91.43% |
| 77 | Z.AI GLM 5.3 (Reasoning, Max) | 95.30% | 85.91% | 100.00% | 100.00% | 95.20% |
| 78 | DeepSeek V4.1 Flash (Reasoning, High) | 95.27% | 85.81% | 100.00% | 100.00% | 94.30% |
| 79 | DeepSeek V4 Pro (Reasoning) | 95.25% | 86.88% | 100.00% | 98.89% | 89.28% |
| 80 | GPT-5.4 (Reasoning) | 95.22% | 85.65% | 100.00% | 100.00% | 93.85% |
| 81 | Z.AI GLM 5.3 Flash (Reasoning, Max) | 95.12% | 85.36% | 100.00% | 100.00% | 94.28% |
| 82 | Gemma 4 31B | 95.09% | 85.26% | 100.00% | 100.00% | 85.23% |
| 83 | Claude Sonnet 4.6 | 94.99% | 84.99% | 100.00% | 99.97% | 90.66% |
| 84 | GPT-5.6 Terra (Reasoning, Medium) | 94.98% | 84.95% | 100.00% | 100.00% | 92.49% |
| 85 | GPT-6.1 Sol (Reasoning, Medium) | 94.90% | 88.28% | 96.43% | 100.00% | 95.88% |
| 86 | MiniMax M2.5 | 94.72% | 84.66% | 100.00% | 99.50% | 86.71% |
| 87 | MiniMax M2.7 | 94.69% | 84.34% | 100.00% | 99.72% | 86.23% |
| 88 | Gemini 3.1 Pro (Preview) | 94.53% | 83.59% | 100.00% | 100.00% | 94.08% |
| 89 | Kimi K2.6 | 94.43% | 83.28% | 100.00% | 100.00% | 92.57% |
| 90 | Z.AI GLM 4.6 | 94.42% | 84.38% | 100.00% | 98.89% | 87.64% |
| 91 | Thinking Machines Inkling Small (Reasoning, High) | 94.39% | 83.20% | 100.00% | 99.98% | 87.39% |
| 92 | DeepSeek V4 Flash 0731 (Reasoning, High) | 94.32% | 90.10% | 92.86% | 99.98% | 87.97% |
| 93 | Z.AI GLM 4.7 | 94.23% | 82.73% | 100.00% | 99.96% | 87.67% |
| 94 | Gemma 4 26B | 94.22% | 82.67% | 100.00% | 100.00% | 84.89% |
| 95 | Hy4 Preview (Reasoning, High) | 94.17% | 82.50% | 100.00% | 100.00% | 94.80% |
| 96 | Aion 3.0 Mini | 94.08% | 88.15% | 95.24% | 98.85% | 83.69% |
| 97 | Qwen 3.6 35B | 94.07% | 83.33% | 100.00% | 98.89% | 87.66% |
| 98 | ByteDance Seed 2.0 Mini | 94.07% | 82.30% | 100.00% | 99.90% | 85.69% |
| 99 | Qwen 3.7 Flash (Reasoning) | 94.02% | 83.28% | 100.00% | 98.78% | 88.56% |
| 100 | Ministral 3 8B | 94.02% | 82.06% | 100.00% | 100.00% | 69.98% |
| 101 | Kimi K2.5 | 94.01% | 82.03% | 100.00% | 100.00% | 90.86% |
| 102 | Z.AI GLM 4.5 Air | 94.00% | 83.12% | 100.00% | 98.87% | 80.74% |
| 103 | Muse Wonder (Reasoning, Medium) | 93.92% | 81.77% | 100.00% | 100.00% | 95.47% |
| 104 | GPT-6 Sol (Reasoning, Medium) | 93.91% | 81.72% | 100.00% | 100.00% | 92.63% |
| 105 | Claude Opus 5 | 93.91% | 81.72% | 100.00% | 100.00% | 89.97% |
| 106 | Xiaomi MIMO v2.6 Pro | 93.78% | 81.51% | 100.00% | 99.84% | 91.50% |
| 107 | GPT-5.6 Luna | 93.37% | 80.10% | 100.00% | 100.00% | 85.06% |
| 108 | Qwen 3.5 122B | 93.29% | 79.87% | 100.00% | 100.00% | 90.32% |
| 109 | Qwen 3.5 27B | 93.29% | 79.86% | 100.00% | 100.00% | 90.05% |
| 110 | Inception Mercury 2 | 93.22% | 98.13% | 81.55% | 99.99% | 81.99% |
| 111 | Mistral Small 4 (Reasoning) | 93.18% | 83.11% | 96.43% | 100.00% | 79.48% |
| 112 | Laguna S 2.1 | 93.17% | 79.51% | 100.00% | 100.00% | 79.99% |
| 113 | Aion 2.0 | 93.10% | 86.41% | 92.89% | 100.00% | 86.66% |
| 114 | Gemini 2.5 Pro | 93.05% | 79.16% | 100.00% | 100.00% | 88.44% |
| 115 | GPT-5 Nano | 92.99% | 90.90% | 88.10% | 99.96% | 80.16% |
| 116 | Claude Opus 4.7 | 92.95% | 78.84% | 100.00% | 100.00% | 89.90% |
| 117 | Qwen 3.8 Max (Reasoning, XHigh) | 92.76% | 78.28% | 100.00% | 100.00% | 96.21% |
| 118 | Thinking Machines Inkling | 92.70% | 78.10% | 100.00% | 100.00% | 73.96% |
| 119 | Gemini 3 Flash (Preview, Reasoning) | 92.65% | 77.99% | 100.00% | 99.97% | 89.93% |
| 120 | GPT-6 Luna | 92.57% | 77.71% | 100.00% | 100.00% | 83.73% |
| 121 | GPT-5.5 (Reasoning, Medium) | 92.12% | 76.35% | 100.00% | 100.00% | 93.72% |
| 122 | Laguna XS 2.1 | 92.09% | 83.48% | 92.86% | 99.93% | 75.42% |
| 123 | Claude Haiku 4.5 | 91.93% | 75.80% | 100.00% | 100.00% | 83.36% |
| 124 | Ministral 8B | 91.89% | 75.68% | 100.00% | 100.00% | 63.77% |
| 125 | Z.AI GLM 4.5 | 91.83% | 76.65% | 100.00% | 98.85% | 84.95% |
| 126 | Qwen 3.5 9B | 91.81% | 81.32% | 96.43% | 97.67% | 84.05% |
| 127 | GPT-5.6 Sol (Reasoning, Medium) | 91.72% | 75.16% | 100.00% | 100.00% | 95.15% |
| 128 | Qwen 3.8 Flash (Reasoning) | 91.39% | 75.27% | 100.00% | 98.89% | 94.24% |
| 129 | GPT-5.5 (Reasoning, Low) | 91.37% | 74.11% | 100.00% | 100.00% | 92.51% |
| 130 | Claude Haiku 5.5 (Reasoning, Medium) | 91.20% | 97.41% | 76.19% | 100.00% | 84.17% |
| 131 | Claude Opus 4.5 | 91.03% | 73.09% | 100.00% | 100.00% | 89.60% |
| 132 | ByteDance Seed 1.6 Flash | 90.83% | 83.03% | 89.88% | 99.57% | 70.92% |
| 133 | GPT-5.6 Terra | 90.63% | 71.90% | 100.00% | 100.00% | 88.23% |
| 134 | Mistral Large 4.0 | 90.47% | 71.55% | 100.00% | 99.87% | 84.72% |
| 135 | Qwen 3.8 27B (Reasoning, XHigh) | 90.29% | 75.31% | 100.00% | 95.56% | 92.91% |
| 136 | GPT-5.5 | 90.28% | 70.85% | 100.00% | 100.00% | 89.37% |
| 137 | GPT-4.1 Nano | 90.07% | 70.27% | 100.00% | 99.95% | 69.90% |
| 138 | Claude Sonnet 4 | 90.04% | 70.11% | 100.00% | 100.00% | 87.64% |
| 139 | Qwen 3.5 397B A17B | 90.04% | 70.17% | 100.00% | 99.93% | 91.09% |
| 140 | Z.AI GLM 4.7 Flash | 90.00% | 77.13% | 92.86% | 100.00% | 82.21% |
| 141 | Claude Haiku 5.5 (Reasoning, Low) | 89.61% | 98.59% | 70.24% | 100.00% | 84.75% |
| 142 | Gemini 3.5 Flash (Reasoning, Minimal) | 89.55% | 68.64% | 100.00% | 100.00% | 85.88% |
| 143 | ByteDance Seed 2.0 Lite | 89.50% | 70.73% | 100.00% | 97.78% | 84.27% |
| 144 | Mistral Medium 3.5 (Reasoning) | 89.37% | 68.10% | 100.00% | 100.00% | 85.32% |
| 145 | DeepSeek V4 Pro | 89.36% | 68.09% | 100.00% | 99.98% | 82.05% |
| 146 | GPT-6 Sol | 89.32% | 67.97% | 100.00% | 100.00% | 90.05% |
| 147 | Qwen 3.5 35B | 89.24% | 74.87% | 92.86% | 100.00% | 87.01% |
| 148 | Qwen 3 32B | 89.06% | 67.79% | 100.00% | 99.39% | 79.37% |
| 149 | Mistral Medium 3.1 | 88.93% | 66.78% | 100.00% | 100.00% | 76.08% |
| 150 | DeepSeek V4 Pro 0813 (Reasoning, High) | 88.77% | 74.61% | 92.88% | 98.82% | 90.21% |
| 151 | Claude Sonnet 5 | 88.74% | 66.23% | 100.00% | 100.00% | 87.34% |
| 152 | Qwen 3.5 Flash | 88.70% | 73.21% | 92.90% | 99.98% | 85.66% |
| 153 | Nemotron 3 Nano | 88.55% | 85.80% | 82.14% | 97.72% | 74.50% |
| 154 | Arcee AI: Trinity Mini | 88.35% | 65.05% | 100.00% | 100.00% | 67.68% |
| 155 | Gemini 2.5 Flash Lite | 88.08% | 64.28% | 100.00% | 99.96% | 79.91% |
| 156 | Gemini 3.1 Flash Lite | 87.86% | 63.57% | 100.00% | 100.00% | 85.09% |
| 157 | Claude Opus 4 | 87.84% | 63.52% | 100.00% | 100.00% | 87.22% |
| 158 | Grok 4.3 | 87.79% | 63.41% | 100.00% | 99.96% | 78.00% |
| 159 | Claude Sonnet 4.5 | 87.78% | 63.35% | 100.00% | 100.00% | 87.54% |
| 160 | DeepSeek V4 Flash | 87.73% | 63.20% | 100.00% | 100.00% | 82.02% |
| 161 | Gemini 3.1 Flash Lite (Reasoning) | 87.63% | 62.89% | 100.00% | 100.00% | 85.91% |
| 162 | Mistral Medium 3.5 | 87.58% | 62.75% | 100.00% | 100.00% | 84.52% |
| 163 | Gemini 3.5 Flash Lite (Reasoning, Minimal) | 87.57% | 62.72% | 100.00% | 100.00% | 84.45% |
| 164 | Gemini 3.5 Flash Lite (Reasoning) | 87.49% | 62.47% | 100.00% | 100.00% | 84.34% |
| 165 | Gemini 3.1 Flash Lite (Preview) | 87.29% | 61.89% | 100.00% | 99.97% | 85.41% |
| 166 | Hermes 3 405B | 87.02% | 61.06% | 100.00% | 100.00% | 80.80% |
| 167 | GPT-5.4 Nano | 86.86% | 60.58% | 100.00% | 100.00% | 72.16% |
| 168 | Mistral Small 3.2 24B | 86.84% | 62.38% | 100.00% | 98.14% | 77.36% |
| 169 | Qwen 3.5 Plus (2026-02-15) | 86.62% | 60.20% | 100.00% | 99.65% | 86.17% |
| 170 | GPT-5.4 | 86.32% | 58.96% | 100.00% | 100.00% | 84.31% |
| 171 | DeepSeek V3.2 | 86.25% | 58.75% | 100.00% | 100.00% | 82.22% |
| 172 | GPT-4.1 Mini | 86.23% | 58.70% | 100.00% | 100.00% | 81.40% |
| 173 | GPT-4o, Aug. 6th (temp=1) | 86.00% | 58.17% | 100.00% | 99.82% | 81.28% |
| 174 | DeepSeek V3 (2024-12-26) | 85.69% | 57.07% | 100.00% | 100.00% | 82.62% |
| 175 | Gemini 3 Flash (Preview) | 85.61% | 56.88% | 100.00% | 99.95% | 85.47% |
| 176 | DeepSeek V3.1 | 85.55% | 56.76% | 100.00% | 99.89% | 82.35% |
| 177 | Qwen 2.5 72B | 85.54% | 58.36% | 100.00% | 98.28% | 73.17% |
| 178 | Mistral Large 2 | 85.45% | 56.35% | 100.00% | 100.00% | 81.50% |
| 179 | GPT-4o Mini (temp=1) | 85.28% | 55.83% | 100.00% | 100.00% | 77.82% |
| 180 | Gemini 2.5 Flash | 85.27% | 56.72% | 100.00% | 99.08% | 80.61% |
| 181 | Cydonia 24B V4.1 | 85.22% | 66.97% | 91.07% | 97.62% | 72.68% |
| 182 | Mistral Large 3 | 85.18% | 55.54% | 100.00% | 100.00% | 84.29% |
| 183 | GPT-4o, Aug. 6th (temp=0) | 83.33% | 50.00% | 100.00% | 100.00% | 82.18% |
| 184 | Ministral 3 14B | 83.19% | 49.57% | 100.00% | 100.00% | 70.45% |
| 185 | DeepSeek-V2 Chat | 82.48% | 56.98% | 90.48% | 100.00% | 84.09% |
| 186 | GPT-4o Mini (temp=0) | 82.23% | 46.70% | 100.00% | 100.00% | 76.86% |
| 187 | GPT-5.4 Mini | 81.85% | 45.55% | 100.00% | 100.00% | 80.45% |
| 188 | Mistral Small 4 | 81.83% | 45.50% | 100.00% | 100.00% | 75.23% |
| 189 | Gemma 3 27B | 80.53% | 41.59% | 100.00% | 100.00% | 75.70% |
| 190 | Writer: Palmyra X5 | 80.49% | 48.62% | 92.86% | 100.00% | 78.11% |
| 191 | Grok 4.20 | 80.48% | 41.45% | 100.00% | 99.99% | 81.21% |
| 192 | Llama 3.1 70B | 80.47% | 61.33% | 92.86% | 87.24% | 77.41% |
| 193 | WizardLM 2 8x22b | 79.28% | 57.02% | 85.73% | 95.09% | 71.45% |
| 194 | Gemma 3 12B | 77.13% | 31.38% | 100.00% | 100.00% | 76.07% |
| 195 | DeepSeek V3 (2025-03-24) | 76.88% | 47.98% | 88.10% | 94.58% | 79.93% |
| 196 | Qwen 3 235B A22B Instruct 2507 | 76.34% | 43.34% | 85.71% | 99.97% | 78.07% |
| 197 | Gemma 3 4B | 75.94% | 27.83% | 100.00% | 100.00% | 66.33% |
| 198 | Ministral 3 3B | 75.10% | 36.00% | 89.29% | 100.00% | 65.02% |
| 199 | Ministral 3B | 73.79% | 35.66% | 85.71% | 100.00% | 59.25% |
| 200 | Hermes 3 70B | 70.71% | 53.99% | 60.79% | 97.34% | 69.74% |
| 201 | Mistral NeMO | 69.32% | 31.81% | 76.19% | 99.97% | 63.80% |
| 202 | Cohere Command R+ (Aug. 2024) | 66.30% | 61.00% | 37.90% | 100.00% | 67.04% |