MLVU-Test - Sports QA: leaderboard
MLVU-Test Sports QA (SQA): the model must answer questions about specific moments in long sports videos (added for the test set), choosing among six options. Scored as accuracy in percent on the held-out long-video test set; higher is better (BAAI, CVPR 2025).
Metric: Multiple-choice accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 63.6 | #741 |
| 2 | Claude 3 Opus | 47.2 | #1459 |
| 3 | Qwen-VL-Max | 44.4 | #1226 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mlvu-test-sports-qa · How It Works · Data refreshed daily, snapshot 2026-11-12.