← back to paper

Review history

arxiv: 2507.18342 · 2 revisions

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 7.0
   137403 ms 25684 in 13703 out 2026-08-15T18:14:19.888169+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   146682 ms 25684 in 15692 out 2026-08-06T14:33:48.651011+00:00