ReactBench (Hallucination) - Dense Counting (CoT): leaderboard
Accuracy in percent on ReactBench (2026) questions about crowded images that require counting, with a step-by-step reasoning prompt; an incorrect answer counts as a hallucination. Higher is better.
Metric: Accuracy (%) on Dense Counting (12,248 questions on 1,531 crowded images) with a step-by-step reasoning prompt, 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) | 64 | #577 |
| 2 | Qwen 3.5 27B | 61.8 | #380 |
| 3 | Qwen 3 VL 32B Instruct | 58.3 | #607 |
| 4 | InternVL3-8B | 57.8 | #1795 |
| 5 | Qwen 3.5 9B | 56.1 | #838 |
| 6 | Qwen 2.5 VL 72B Instruct | 54.9 | #849 |
| 7 | ReactBench MiMo-VL-7B (checkpoint unspecified) | 53.7 | |
| 8 | ReactBench LLaVA-OV-7B (checkpoint unspecified) | 48.4 | |
| 9 | Qwen 2.5 VL 7B Instruct | 47.8 | #1919 |
| 10 | Qwen 3 VL 4B | 46.6 | #1163 |
| 11 | InternVL2.5-26B | 46.4 | #2174 |
| 12 | InternVL2.5-8B | 43.2 | #2393 |
| 13 | ReactBench LLaVA-v1.6-7B (checkpoint unspecified) | 33.1 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=reactbench-hallucination-dense-counting-cot · How It Works · Data refreshed daily, snapshot 2026-11-22.