EgoSchema — leaderboard
EgoSchema: Evaluates temporal, video, speech, or audio understanding beyond static text and image inputs.
Metric: Accuracy (%). Source: egoschema.github.io. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Reality Distortion | 80.76 |
| 2 | ft_llava_72B | 80.6 |
| 3 | PCIE | 78.63 |
| 4 | iLearn2.0 | 76.61 |
| 5 | ccego | 75.95 |
| 6 | Noah's_Ark_Lab | 75.27 |
| 7 | iLearn | 74.82 |
| 8 | GMMV | 73.58 |
| 9 | uceezzz2 | 73.39 |
| 10 | GogoEgo | 72.25 |
Interactive version: theaggregate.ai/benchmark?slug=egoschema · How the rankings work · Data refreshed daily, snapshot 2026-07-22.