Oryx-1.5: benchmark results

Provider: Other.

Aggregate Rating 1546 ± 50, rank #1754 of 10916 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Video-MME - Long Videos (w/ subs)69.9Accuracy (%)86
Video-MME - Medium Videos (w/ subs)74.3Accuracy (%)84
Video-MME - Short Videos (w/ subs)80.6Accuracy (%)78
VideoMME w sub.74.9Score (imported)76.4
Video-MME - Long Videos (w/o subs)59.3Accuracy (%)74
Video-MME - Short Videos (w/o subs)77.3Accuracy (%)70
Video-MME - Medium Videos (w/o subs)65.3Accuracy (%)68
V-STaR - Long mAM11.89Score46.2
V-STaR - Long mLGM13.99Score46.2
V-STaR14.47Average All Score15.4
V-STaR - All mAM15.11Score15.4
V-STaR - Medium mAM14.83Score15.4

Interactive version: theaggregate.ai/model?slug=oryx-1-5 · How It Works · Data refreshed daily, snapshot 2026-11-08.