MM-JudgeBias - Image Misalignment: 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-Deviation from 0 to 1, the normalized score drop when the image is swapped for an unrelated one; higher is better.
Metric: Bias-Deviation (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 drop of the judge's score, normalized by the largest possible drop, when the image is replaced with an unrelated one; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 26 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 0.973 | #160 | |
| 2 | Gemini 3 Pro | High | 0.955 | #145 |
| 3 | Claude Sonnet 4.5 | Thinking | 0.905 | #261 |
| 4 | Gemini 2.5 Pro | 0.904 | #276 | |
| 5 | Claude Haiku 4.5 | 0.818 | #583 | |
| 6 | Gemini 2.5 Flash | 0.76 | #463 | |
| 7 | Qwen 3 VL 30B A3B Instruct | 0.648 | #895 | |
| 8 | Gemini 2.5 Flash Lite | Thinking | 0.634 | #964 |
| 9 | Qwen 3 VL 8B Instruct | 0.622 | #1029 | |
| 10 | Qwen 3 VL 8B (Thinking) | 0.529 | #910 | |
| 11 | Qwen 3 VL 30B A3B (Thinking) | 0.476 | #719 | |
| 12 | InternVL3.5-14B | 0.464 | #1504 | |
| 13 | LLaVA-Critic-7B | 0.452 | ||
| 14 | InternVL3.5-30B-A3B | 0.377 | #1267 | |
| 15 | O3 | High | 0.337 | #237 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mm-judgebias-image-misalignment · How It Works · Data refreshed daily, snapshot 2026-11-21.