MM-JudgeBias - Detail Description: leaderboard
MM-JudgeBias (2026) tests multimodal LLM judges for compositional bias: the judge scores image, query and response triplets from 1 to 10 before and after a controlled perturbation. Bias-Conformity from 0 to 1, the stability of the score when a detailed caption of the image is appended to the query; higher is better.
Metric: Bias-Conformity (0 to 1) on MM-JudgeBias (about 200 image-query-response triplets per bias type, 1,804 in all, each judged on a 1-10 scale before and after a controlled perturbation; mean of three runs): mean score invariance (1 minus the absolute score change over its largest possible value) when a detailed caption of the image is appended to the query; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 26 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | High | 0.936 | #146 |
| 2 | Gemini 2.5 Pro | 0.935 | #280 | |
| 3 | LLaVA-Critic-72B | 0.926 | ||
| 4 | Claude Opus 4.5 | Thinking | 0.917 | #165 |
| 5 | GPT-5.1 | High | 0.911 | #248 |
| 6 | Gemini 2.5 Flash | 0.905 | #466 | |
| 7 | GPT-5 Mini | High | 0.898 | #373 |
| 8 | Gemini 2.0 Flash Lite | 0.897 | #1064 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 0.886 | #727 | |
| 10 | O4 Mini | High | 0.886 | #372 |
| 11 | Claude Sonnet 4.5 | Thinking | 0.884 | #267 |
| 12 | Qwen 3 VL 8B (Thinking) | 0.883 | #924 | |
| 13 | GPT-4.1 Mini | 0.882 | #799 | |
| 14 | O3 | High | 0.879 | #242 |
| 15 | Claude Haiku 4.5 | Thinking | 0.87 | #587 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mm-judgebias-detail-description · How It Works · Data refreshed daily, snapshot 2026-11-22.