Hallucinations Leaderboard: leaderboard

Public leaderboard evaluating LLM factuality, faithfulness, hallucination detection, instruction following, QA, reading comprehension, and summarization tasks.

Metric: Average Task Score (score). Source: huggingface.co. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 42 models tracked.

Top models

#ModelScoreOverall rank
1zephyr-7B-alpha52.08#1276
2Mistral 7B Instruct (v0.2)51.63#1311
3Mistral Instruct v0.1 7B50.48#1438
4Llama 2 13B Base49.78#1425
5zephyr-7B-beta49.62#1313
6Nous-Hermes-llama-2-7B46.65#1462
7Llama 2 7B Chat46.54#1479
8Yarn-Mistral-7B-128k46.29#1388
9Llama 2 13B Chat45.52#1415
10gemma-7B44.42#1346
11Orca-2-13B44.31#1426
12Llama 2 7B Base44.23#1497
13Mistral-7B-v0.144.06#1295
14SOLAR-10.7B-Instruct-v1.043.71#1066
15falcon-7B Instruct40.57#1604

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=hallucinations-leaderboard · How It Works · Data refreshed daily, snapshot 2026-11-06.