MMOOC - Multimodal Ambiguity (Open-Ended VQA): leaderboard

Metric: Out-of-context score (%; mean of the refusal rate, the share of the Multimodal Ambiguity Open-Ended VQA questions, which the image and context cannot answer, that the model correctly declines, and refusal rationality, the mean 0-1 judge score of its abstention reasoning in steps of 0.25; judge scores averaged over GPT-5.6, Claude Opus 5 and DeepSeek-V4-Pro). Source: arxiv.org. Saturation forecast: Around 2030. 18 models tracked.

Top models

#ModelScore
1Gemma 4 26B79.25
2O175
3Gemma 4 31B71.5
4Ministral 3 8B54.5
5Ministral 3 14B52.5
6Llama 4 Maverick52.25
7O347.75
8Qwen 3.5 27B46
9Qwen 3.5 122B A10B46
10GPT-4o43.5
11InternVL3-8B21.75
12Claude Opus 4.614.75
13Gemini 3.1 Pro (Preview)7.75

Interactive version: theaggregate.ai/benchmark?slug=mmooc-multimodal-ambiguity-open-ended-vqa · How It Works · Data refreshed daily, snapshot 2026-09-29.