Video-XL: benchmark results
Provider: Other.
Aggregate Rating 1483 ± 46, rank #2583 of 10556 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MLVU-Test - Action Order | 48.6 | Multiple-choice accuracy (%) | 92.6 |
| MLVU-Dev - Generation | 4.5 | Generation score, GPT-4 judged (0-10) | 89.7 |
| MLVU-Test - Action Count | 31.7 | Multiple-choice accuracy (%) | 88.2 |
| MLVU-Test - Generation | 4.21 | Generation score, GPT-4 judged (0-10) | 87.5 |
| MLVU-Test - Tutorial QA | 44.2 | Multiple-choice accuracy (%) | 85.3 |
| MLVU-Test - Needle QA | 50 | Multiple-choice accuracy (%) | 79.4 |
| MLVU-Dev | 64.9 | Multiple-choice accuracy (%) | 78.9 |
| MLVU-Test | 45.5 | Multiple-choice accuracy (%) | 70.6 |
| MLVU-Test - Sports QA | 41.6 | Multiple-choice accuracy (%) | 67.6 |
| MLVU-Test - Ego Reasoning | 41.5 | Multiple-choice accuracy (%) | 64.7 |
| MLVU-Test - Plot QA | 46 | Multiple-choice accuracy (%) | 61.8 |
| MLVU-Test - Topic Reasoning | 78 | Multiple-choice accuracy (%) | 58.8 |
Interactive version: theaggregate.ai/model?slug=video-xl · How It Works · Data refreshed daily, snapshot 2026-11-17.