ReactBench (Hallucination): leaderboard
ReactBench (2026) probes multimodal hallucination with about 50,000 questions on images edited to contradict language priors. React-Score in percent weights short-answer, multiple-choice and yes-or-no accuracy, averages standard and chain-of-thought prompting and weights the four tasks; higher is better.
Metric: React-Score (%): question-type-weighted accuracy (short answer 0.5, multiple choice and yes/no 0.25 each), averaged over standard and chain-of-thought prompting (thinking-only models: chain-of-thought) and weighted over the four tasks (0.3, 0.2, 0.2, 0.3), hallucination-inducing questions (multiple choice, short answer, yes/no) about images edited by Qwen-Image-Edit-2511; an incorrect answer counts as a hallucination; temperature 0.2, at most 1,024 tokens, LLM answer matching; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 32B (Thinking) | 65.3 | #573 |
| 2 | Qwen 3 VL 32B Instruct | 61.9 | #606 |
| 3 | Qwen 3.5 27B | 59.5 | #375 |
| 4 | ReactBench MiMo-VL-7B (checkpoint unspecified) | 57.5 | |
| 5 | InternVL3-8B | 56.5 | #1782 |
| 6 | Qwen 2.5 VL 72B Instruct | 54.2 | #841 |
| 7 | Qwen 3 VL 4B | 54 | #1151 |
| 8 | Qwen 3.5 9B | 52.4 | #828 |
| 9 | Qwen 2.5 VL 7B Instruct | 49.5 | #1902 |
| 10 | InternVL2.5-26B | 47 | #2156 |
| 11 | ReactBench LLaVA-OV-7B (checkpoint unspecified) | 42 | |
| 12 | InternVL2.5-8B | 41.5 | #2370 |
| 13 | ReactBench LLaVA-v1.6-7B (checkpoint unspecified) | 34.5 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=reactbench-hallucination · How It Works · Data refreshed daily, snapshot 2026-11-21.