MMOOC - Partial Answerability (Yes/No): leaderboard
MMOOC also tests answering under shifted context, where the question is still answerable from the image. This board covers yes or no questions where only some sub-queries of the question are supported by the image, and averages accuracy with a judge rating of correctness and evidence consistency in the answer.
Metric: Shifted in-context score (%; mean of accuracy on the answerable Partial Answerability Yes/No questions and answer rationality, the mean 0-1 judge score of the answer's correctness and evidence consistency in steps of 0.25; judge scores averaged over GPT-5.6, Claude Opus 5 and DeepSeek-V4-Pro). Source: arxiv.org. Saturation forecast: Not forecast. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 82.75 | #102 |
| 2 | O1 | 81.25 | #393 |
| 3 | Ministral 3 14B | 81 | #1845 |
| 4 | Gemma 4 26B | 79 | #612 |
| 5 | GPT-4o | 78.25 | #741 |
| 6 | Qwen 3.5 122B A10B | 78.25 | #331 |
| 7 | Gemma 4 31B | 77.25 | #394 |
| 8 | O3 | 77.25 | #228 |
| 9 | Qwen 3.5 27B | 75.75 | #359 |
| 10 | Llama 4 Maverick | 74.25 | #1099 |
| 11 | Ministral 3 8B | 72.75 | #2023 |
| 12 | InternVL3-8B | 66.75 | #1688 |
| 13 | Gemini 3.1 Pro (Preview) | 62.75 | #94 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mmooc-partial-answerability-yes-no · How It Works · Data refreshed daily, snapshot 2026-11-13.