ReactBench (Hallucination) - Alteration Tracing (Standard): leaderboard
Metric: Accuracy (%) on Alteration Tracing (10,956 questions on 913 before-and-after image pairs) with standard prompting, 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 January 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 79.9 |
| 2 | Qwen 3 VL 32B Instruct | 73.5 |
| 3 | Qwen 3.5 9B | 67.4 |
| 4 | InternVL3-8B | 64.1 |
| 5 | Qwen 2.5 VL 72B Instruct | 62.1 |
| 6 | Qwen 2.5 VL 7B Instruct | 54 |
Interactive version: theaggregate.ai/benchmark?slug=reactbench-hallucination-alteration-tracing-standard · How It Works · Data refreshed daily, snapshot 2026-10-07.