Video-XL: benchmark results

Provider: Other.

Aggregate Rating 1483 ± 46, rank #2583 of 10556 rated models, from 21 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MLVU-Test - Action Order48.6Multiple-choice accuracy (%)92.6
MLVU-Dev - Generation4.5Generation score, GPT-4 judged (0-10)89.7
MLVU-Test - Action Count31.7Multiple-choice accuracy (%)88.2
MLVU-Test - Generation4.21Generation score, GPT-4 judged (0-10)87.5
MLVU-Test - Tutorial QA44.2Multiple-choice accuracy (%)85.3
MLVU-Test - Needle QA50Multiple-choice accuracy (%)79.4
MLVU-Dev64.9Multiple-choice accuracy (%)78.9
MLVU-Test45.5Multiple-choice accuracy (%)70.6
MLVU-Test - Sports QA41.6Multiple-choice accuracy (%)67.6
MLVU-Test - Ego Reasoning41.5Multiple-choice accuracy (%)64.7
MLVU-Test - Plot QA46Multiple-choice accuracy (%)61.8
MLVU-Test - Topic Reasoning78Multiple-choice accuracy (%)58.8

Interactive version: theaggregate.ai/model?slug=video-xl · How It Works · Data refreshed daily, snapshot 2026-11-17.