ClinHallu - Reasoning Integration Hallucination: leaderboard
Metric: Reasoning integration hallucination rate (%): share of items whose reasoning stage, generated after the reference visual and knowledge stages are supplied, the judge marks as hallucinated, macro-averaged over the ClinHallu test items of VQA-RAD, PathVQA, MedFrameQA and MedXpertQA (medical VQA with validated reference traces of visual recognition, knowledge recall and reasoning integration); the model writes a structured trace and answer (temperature 0.7) and a Qwen3.5-27B judge grades them (temperature 0.01); lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 2.3 |
| 2 | Qwen 3 VL 32B | 4.4 |
| 3 | Qwen 3.5 9B | 4.8 |
| 4 | Qwen 3.5 4B | 5.1 |
| 5 | InternVL3.5-8B | 6.6 |
| 6 | Lingshu-7B | 13.6 |
| 7 | Qwen 2.5 VL 7B Instruct | 18.1 |
| 8 | MedGemma-4B-IT | 30.5 |
Interactive version: theaggregate.ai/benchmark?slug=clinhallu-reasoning-integration-hallucination · How It Works · Data refreshed daily, snapshot 2026-09-29.