Content Invention
Subcategory of Hallucination. 116 models scored.
Model Leaderboard
All models ranked by their Content Invention subcategory score.
| # | Model | Content Invention | Hallucination | Overall |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 (Reasoning) | 100.00% | 98.13% | 95.02% |
| 2 | Gemini 3.1 Pro (Preview) | 100.00% | 89.06% | 94.37% |
| 3 | Z.AI GLM 5 Turbo | 100.00% | 98.64% | 94.27% |
| 4 | Claude Sonnet 4.6 (Reasoning) | 100.00% | 93.96% | 93.66% |
| 5 | GPT-5.4 (Reasoning) | 100.00% | 90.43% | 93.24% |
| 6 | GPT-5 Mini | 100.00% | 97.71% | 92.62% |
| 7 | GPT-5.1 | 100.00% | 98.44% | 92.54% |
| 8 | Claude Opus 4.6 | 100.00% | 93.60% | 92.35% |
| 9 | GPT-5 | 100.00% | 91.84% | 91.93% |
| 10 | Qwen 3.5 397B A17B | 100.00% | 82.10% | 91.73% |
| 11 | Qwen 3.5 122B | 100.00% | 86.58% | 91.53% |
| 12 | Grok 4.20 (Beta, Reasoning) | 100.00% | 96.28% | 91.49% |
| 13 | GPT-5.4 (Reasoning, Low) | 100.00% | 92.29% | 91.41% |
| 14 | Z.AI GLM 5 | 100.00% | 97.74% | 91.23% |
| 15 | Claude Sonnet 4.6 | 100.00% | 89.99% | 91.15% |
| 16 | MoonshotAI: Kimi K2.5 | 100.00% | 88.02% | 91.04% |
| 17 | Qwen 3.5 27B | 100.00% | 86.58% | 90.85% |
| 18 | ByteDance Seed 1.6 | 100.00% | 95.14% | 90.70% |
| 19 | GPT-5.4 Mini (Reasoning) | 100.00% | 96.22% | 90.65% |
| 20 | Gemini 3 Flash (Preview, Reasoning) | 100.00% | 85.32% | 90.50% |
| 21 | o4 Mini High | 100.00% | 99.06% | 90.29% |
| 22 | GPT-5.2 | 100.00% | 95.09% | 90.26% |
| 23 | Claude Opus 4.5 | 100.00% | 82.06% | 89.69% |
| 24 | Grok 4.1 Fast | 100.00% | 99.02% | 89.55% |
| 25 | Z.AI GLM 4.6 | 100.00% | 90.08% | 89.11% |
| 26 | MiniMax M2.7 | 100.00% | 96.47% | 89.10% |
| 27 | Gemini 3 Pro (Preview) | 100.00% | 88.23% | 88.79% |
| 28 | Claude Sonnet 4 | 100.00% | 80.08% | 88.72% |
| 29 | MiniMax M2.5 | 100.00% | 92.94% | 88.71% |
| 30 | Z.AI GLM 4.7 | 100.00% | 88.47% | 88.69% |
| 31 | GPT-4.1 | 100.00% | 95.24% | 88.68% |
| 32 | Gemini 2.5 Pro | 100.00% | 86.11% | 88.53% |
| 33 | o4 Mini | 100.00% | 98.75% | 88.35% |
| 34 | Grok 4 | 100.00% | 89.45% | 88.12% |
| 35 | Claude Sonnet 4.5 | 100.00% | 75.57% | 88.03% |
| 36 | Claude Opus 4 | 100.00% | 75.68% | 87.69% |
| 37 | Stealth: Hunter Alpha | 100.00% | 90.78% | 87.34% |
| 38 | ByteDance Seed 2.0 Mini | 100.00% | 91.33% | 86.91% |
| 39 | Gemini 2.5 Flash (Reasoning) | 100.00% | 95.60% | 86.51% |
| 40 | Z.AI GLM 4.5 | 100.00% | 87.05% | 86.27% |
| 41 | Grok 4 Fast | 100.00% | 91.09% | 86.15% |
| 42 | Qwen 3.5 Plus (2026-02-15) | 100.00% | 73.35% | 85.96% |
| 43 | Stealth: Healer Alpha | 100.00% | 94.67% | 85.93% |
| 44 | Gemini 3.1 Flash Lite (Preview) | 100.00% | 74.58% | 85.87% |
| 45 | GPT-5.4 Mini (Reasoning, Low) | 100.00% | 98.43% | 85.75% |
| 46 | Mistral Large 3 | 100.00% | 78.17% | 85.43% |
| 47 | GPT-4o, May 13th (temp=0) | 100.00% | 69.76% | 85.36% |
| 48 | Gemini 3 Flash (Preview) | 100.00% | 71.24% | 85.35% |
| 49 | Claude Haiku 4.5 | 100.00% | 83.86% | 85.14% |
| 50 | ByteDance Seed 2.0 Lite | 100.00% | 79.75% | 84.80% |
| 51 | Nemotron 3 Super | 100.00% | 99.69% | 84.56% |
| 52 | GPT-5.4 | 100.00% | 73.78% | 84.32% |
| 53 | Claude 3.5 Sonnet | 100.00% | 76.31% | 84.24% |
| 54 | Grok 4.20 (Beta) | 100.00% | 78.28% | 83.85% |
| 55 | GPT-4o, May 13th (temp=1) | 100.00% | 73.40% | 83.80% |
| 56 | DeepSeek V3 (2024-12-26) | 100.00% | 73.11% | 83.68% |
| 57 | Claude 3.7 Sonnet | 100.00% | 75.18% | 83.39% |
| 58 | GPT-4.1 Mini | 100.00% | 81.14% | 83.20% |
| 59 | Hermes 3 405B | 100.00% | 79.70% | 82.86% |
| 60 | GPT-4o, Aug. 6th (temp=1) | 100.00% | 79.53% | 82.62% |
| 61 | GPT-4o, Aug. 6th (temp=0) | 100.00% | 73.35% | 82.45% |
| 62 | GPT-5.4 Mini | 100.00% | 78.40% | 82.43% |
| 63 | Mistral Large 2 | 100.00% | 77.87% | 82.41% |
| 64 | DeepSeek V3.1 | 100.00% | 72.80% | 82.39% |
| 65 | DeepSeek V3.2 | 100.00% | 72.50% | 82.25% |
| 66 | Qwen 3 32B | 100.00% | 89.56% | 82.21% |
| 67 | GPT-5.4 Nano (Reasoning) | 100.00% | 97.95% | 81.36% |
| 68 | Gemini 2.5 Flash Lite | 100.00% | 76.17% | 81.08% |
| 69 | Gemini 2.5 Flash | 100.00% | 71.70% | 80.60% |
| 70 | Mistral Large | 100.00% | 77.50% | 80.15% |
| 71 | GPT-5.4 Nano (Reasoning, Low) | 100.00% | 99.03% | 79.48% |
| 72 | GPT-4o Mini (temp=1) | 100.00% | 76.78% | 79.08% |
| 73 | Mistral Small 3.2 24B | 100.00% | 75.83% | 78.60% |
| 74 | Gemma 3 12B | 100.00% | 69.15% | 78.41% |
| 75 | GPT-4o Mini (temp=0) | 100.00% | 73.56% | 78.29% |
| 76 | Gemma 3 27B | 100.00% | 68.74% | 77.85% |
| 77 | Mistral Medium 3.1 | 100.00% | 82.09% | 77.83% |
| 78 | Mistral Small 4 | 100.00% | 73.41% | 76.46% |
| 79 | Qwen 2.5 72B | 100.00% | 79.56% | 75.46% |
| 80 | GPT-5.4 Nano | 100.00% | 89.29% | 74.40% |
| 81 | Arcee AI: Trinity Large (Preview) | 100.00% | 76.47% | 73.33% |
| 82 | Mistral Small Creative | 100.00% | 74.46% | 73.27% |
| 83 | Ministral 3 14B | 100.00% | 79.99% | 72.54% |
| 84 | GPT-4.1 Nano | 100.00% | 87.73% | 71.94% |
| 85 | Ministral 3 8B | 100.00% | 92.52% | 71.76% |
| 86 | Arcee AI: Trinity Mini | 100.00% | 91.12% | 70.90% |
| 87 | Gemma 3 4B | 100.00% | 67.60% | 68.57% |
| 88 | Ministral 8B | 100.00% | 89.19% | 64.87% |
| 89 | LFM2 24B | 100.00% | 90.53% | 58.77% |
| 90 | Qwen 3.5 9B | 96.43% | 85.58% | 86.05% |
| 91 | Mistral Small 4 (Reasoning) | 96.43% | 92.98% | 82.39% |
| 92 | Llama 3.1 Nemotron 70B | 96.43% | 74.99% | 74.70% |
| 93 | Gemini 2.5 Flash Lite (Reasoning) | 95.24% | 95.59% | 85.75% |
| 94 | Qwen 3.5 Flash | 92.90% | 80.63% | 86.38% |
| 95 | Aion 2.0 | 92.89% | 93.57% | 89.21% |
| 96 | Qwen 3.5 35B | 92.86% | 80.87% | 88.00% |
| 97 | Z.AI GLM 4.7 Flash | 92.86% | 89.86% | 84.82% |
| 98 | Writer: Palmyra X5 | 92.86% | 72.04% | 79.57% |
| 99 | Inception Mercury | 92.86% | 95.08% | 79.50% |
| 100 | Llama 3.1 70B | 92.86% | 69.78% | 78.40% |
| 101 | DeepSeek-V2 Chat | 90.48% | 69.48% | 84.83% |
| 102 | ByteDance Seed 1.6 Flash | 89.88% | 94.52% | 73.27% |
| 103 | Ministral 3 3B | 89.29% | 70.45% | 67.22% |
| 104 | GPT-5 Nano | 88.10% | 93.53% | 82.60% |
| 105 | DeepSeek V3 (2025-03-24) | 88.10% | 67.07% | 81.99% |
| 106 | WizardLM 2 8x22b | 85.73% | 70.24% | 71.07% |
| 107 | Qwen3 235B A22B Instruct 2507 | 85.71% | 69.82% | 80.10% |
| 108 | Ministral 3B | 85.71% | 70.75% | 61.29% |
| 109 | Nemotron 3 Nano | 82.14% | 89.17% | 77.73% |
| 110 | Inception Mercury 2 | 81.55% | 92.60% | 83.85% |
| 111 | Llama 3.1 8B | 77.38% | 43.41% | 63.37% |
| 112 | Mistral NeMO | 76.19% | 62.63% | 65.04% |
| 113 | Claude 3 Haiku | 62.50% | 60.81% | 71.19% |
| 114 | Hermes 3 70B | 60.79% | 67.05% | 72.57% |
| 115 | Rocinante 12B | 38.95% | 52.09% | 54.55% |
| 116 | Cohere Command R+ (Aug. 2024) | 37.90% | 64.40% | 69.03% |