Vectara Hallucination Leaderboard
Vectara Hallucination Leaderboard is run by read by the crawler. It has ranked 111 models, of which the catalogue holds 90, scoring from 3.1 to 24.2 on Hallucination Rate.
measured by read by the crawler · the board itself
| Place | Model | Metric | Score |
|---|---|---|---|
| 2ndof 111 | GPT-5.4 nano | Hallucination Rate | 3.1 |
| 3rdof 111 | Gemini 2.5 Flash-Lite | Hallucination Rate | 3.3 |
| 4thof 111 | Phi-4 | Hallucination Rate | 3.7 |
| 5thof 111 | Llama-3.3-70B-Instruct-Turbo | Hallucination Rate | 4.1 |
| 6thof 111 | DeepSeek V4.1 Flash | Hallucination Rate | 4.2 |
| 8thof 111 | Gemma 3 12B | Hallucination Rate | 4.4 |
| 10thof 111 | Qwen3 8B | Hallucination Rate | 4.8 |
| 11thof 111 | Nova Pro | Hallucination Rate | 5.1 |
| 12thof 111 | Nova 2 Lite | Hallucination Rate | 5.1 |
| 14thof 111 | Granite 4.0 H Small | Hallucination Rate | 5.2 |
| 17thof 111 | DeepSeek V3.2 Exp | Hallucination Rate | 5.3 |
| 18thof 111 | Qwen3 14B | Hallucination Rate | 5.4 |
| 19thof 111 | Nova Micro | Hallucination Rate | 5.5 |
| 20thof 111 | DeepSeek-V3.1 | Hallucination Rate | 5.5 |
| 21stof 111 | GPT-5.4 mini | Hallucination Rate | 5.5 |
| 22ndof 111 | GPT-4.1 fine-tuned | Hallucination Rate | 5.6 |
| 23rdof 111 | Qwen3 4B | Hallucination Rate | 5.7 |
| 24thof 111 | Grok 3 | Hallucination Rate | 5.8 |
| 25thof 111 | Qwen3 32B | Hallucination Rate | 5.9 |
| 26thof 111 | Nova Lite | Hallucination Rate | 6.1 |
| 27thof 111 | DeepSeek-V3 | Hallucination Rate | 6.1 |
| 28thof 111 | DeepSeek v3.2 | Hallucination Rate | 6.3 |
| 29thof 111 | Gemma 3 4B | Hallucination Rate | 6.4 |
| 30thof 111 | GPT 6 Sol | Hallucination Rate | 6.5 |
| 31stof 111 | Command R+ (08-2024) | Hallucination Rate | 6.9 |
| 32ndof 111 | Trinity-Large-Preview | Hallucination Rate | 6.9 |
| 33rdof 111 | GPT-5.4 | Hallucination Rate | 7 |
| 34thof 111 | Gemini 2.5 Pro | Hallucination Rate | 7 |
| 36thof 111 | Gemma 3 27B | Hallucination Rate | 7.4 |
| 37thof 111 | Gemma 4 31B | Hallucination Rate | 7.4 |
| 40thof 111 | Gemini 2.5 Flash | Hallucination Rate | 7.8 |
| 41stof 111 | Llama 4 Maverick 17B | Hallucination Rate | 8.2 |
| 42ndof 111 | Gemini 3.1 Flash-Lite | Hallucination Rate | 8.2 |
| 43rdof 111 | GPT-5.4 Pro | Hallucination Rate | 8.3 |
| 44thof 111 | GPT-5.2 | Hallucination Rate | 8.4 |
| 45thof 111 | DeepSeek V4 Pro | Hallucination Rate | 8.6 |
| 46thof 111 | GPT 6 Astra | Hallucination Rate | 8.7 |
| 47thof 111 | MiniMax M2.5 | Hallucination Rate | 9.1 |
| 48thof 111 | Command A 03-2025 | Hallucination Rate | 9.3 |
| 49thof 111 | GPT-5.5 | Hallucination Rate | 9.3 |
| 51stof 111 | Qwen3 235B A22B | Hallucination Rate | 9.3 |
| 52ndof 111 | Qwen3 Next 80B A3B Thinking | Hallucination Rate | 9.3 |
| 53rdof 111 | GLM-4.7 Flash | Hallucination Rate | 9.3 |
| 55thof 111 | GLM-4.6 | Hallucination Rate | 9.5 |
| 56thof 111 | Nemotron 3 Nano 30B A3B | Hallucination Rate | 9.6 |
| 57thof 111 | GPT-4o (2024-08-06) | Hallucination Rate | 9.6 |
| 59thof 111 | Claude Haiku 4.5 | Hallucination Rate | 9.8 |
| 60thof 111 | Claude Opus 5.5 | Hallucination Rate | 9.9 |
| 61stof 111 | GLM-5 | Hallucination Rate | 10.1 |
| 62ndof 111 | Claude Sonnet 4 | Hallucination Rate | 10.3 |
| 63rdof 111 | Gemini 3.1 Pro Preview | Hallucination Rate | 10.4 |
| 64thof 111 | Qwen3.5-Flash | Hallucination Rate | 10.5 |
| 65thof 111 | Qwen3.5-35B-A3B | Hallucination Rate | 10.5 |
| 66thof 111 | GPT-5 nano | Hallucination Rate | 10.5 |
| 67thof 111 | Claude Sonnet 4.6 | Hallucination Rate | 10.6 |
| 68thof 111 | granite-3.3-8b-instruct | Hallucination Rate | 10.6 |
| 69thof 111 | Qwen3.5 Plus 2026-02-15 | Hallucination Rate | 10.7 |
| 71stof 111 | Kimi K2.6 | Hallucination Rate | 10.8 |
| 72ndof 111 | Claude Opus 4.5 | Hallucination Rate | 10.9 |
| 73rdof 111 | Aya Expanse 32B | Hallucination Rate | 10.9 |
| 74thof 111 | GPT-5.1 | Hallucination Rate | 10.9 |
| 75thof 111 | Qwen3.5-122B-A10B | Hallucination Rate | 11.2 |
| 76thof 111 | DeepSeek-R1 | Hallucination Rate | 11.3 |
| 77thof 111 | GLM-4.7 | Hallucination Rate | 11.7 |
| 78thof 111 | Claude Opus 4.1 | Hallucination Rate | 11.8 |
| 79thof 111 | MiniMax M2.1 | Hallucination Rate | 11.8 |
| 80thof 111 | Claude Opus 4 | Hallucination Rate | 12 |
| 81stof 111 | Claude Sonnet 4.5 | Hallucination Rate | 12 |
| 82ndof 111 | Claude Opus 4.7 | Hallucination Rate | 12 |
| 83rdof 111 | Qwen3.5-27B | Hallucination Rate | 12.1 |
| 85thof 111 | Gemini 4 Argon | Hallucination Rate | 12.1 |
| 86thof 111 | Claude Opus 4.6 | Hallucination Rate | 12.2 |
| 87thof 111 | Mercury 2 | Hallucination Rate | 12.3 |
| 88thof 111 | GPT-5.6 Sol | Hallucination Rate | 12.4 |
| 89thof 111 | MiniMax M2.7 | Hallucination Rate | 12.9 |
| 90thof 111 | GPT-5 mini | Hallucination Rate | 12.9 |
| 91stof 111 | Gemini 3 Flash Preview | Hallucination Rate | 13.5 |
| 92ndof 111 | gemini-3-pro-preview | Hallucination Rate | 13.6 |
| 93rdof 111 | Kimi K2.5 | Hallucination Rate | 14.2 |
| 94thof 111 | GPT OSS 120B | Hallucination Rate | 14.2 |
| 97thof 111 | GPT-5 | Hallucination Rate | 14.7 |
| 99thof 111 | Grok 4.1 Fast Non-Reasoning | Hallucination Rate | 17.8 |
| 101stof 111 | o4-mini | Hallucination Rate | 18.6 |
| 103rdof 111 | Grok 4.1 Fast Reasoning | Hallucination Rate | 19.2 |
| 104thof 111 | Ministral 3 14B 2512 | Hallucination Rate | 19.4 |
| 105thof 111 | grok-4-fast-non-reasoning | Hallucination Rate | 19.7 |
| 107thof 111 | Ministral 3 8B 2512 | Hallucination Rate | 21.7 |
| 109thof 111 | o3-pro | Hallucination Rate | 23.3 |
| 110thof 111 | Phi-4-mini-instruct | Hallucination Rate | 23.5 |
| 111thof 111 | Ministral 3 3B 2512 | Hallucination Rate | 24.2 |
Read from the board on 2026-10-24