ReactBench (Hallucination) - Dense Counting (Standard): leaderboard
Metric: Accuracy (%) on Dense Counting (12,248 questions on 1,531 crowded images) 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 | 69.3 |
| 2 | Qwen 3 VL 32B Instruct | 66.9 |
| 3 | InternVL3-8B | 64.2 |
| 4 | Qwen 2.5 VL 72B Instruct | 63.3 |
| 5 | Qwen 2.5 VL 7B Instruct | 58.6 |
| 6 | Qwen 3.5 9B | 57.2 |
Interactive version: theaggregate.ai/benchmark?slug=reactbench-hallucination-dense-counting-standard · How It Works · Data refreshed daily, snapshot 2026-10-07.