Video-Index
Harbor: pendingA curated meta-benchmark of 840 verified video understanding items selected from a pool of over half a million across 115 benchmarks, designed to resist shortcut attacks.
- Samples
- 840
- Released
- 2026
- Scores
- 10
Video-Arena
Video-Arena A Scalable Agentic Video Benchmark for Spatiotemporal Capability Kuan Zhang1,2, ,‡ Yukun Chen1,3, ,‡ Zhihao Yang1,3, ,‡ Yue Su4 Xiangnan Wu3 Zirong Chen2 Run Luo1,5,‡ Tao Tan1 Yinhe Zheng1,† Yiming Li2,† 1miHoYo…
How to run
ltb · video-arena
$ npm i -g lettokenburn-cli$ ltb bench info video-arena
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
0 sourced entriesNo sourced scores recorded yet.
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
Video-Arena
A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Kuan Zhang1,2,,‡ Yukun Chen1,3,,‡ Zhihao Yang1,3,*,‡ Yue Su4 Xiangnan Wu3 Zirong Chen2 Run Luo1,5,‡ Tao Tan1 Yinhe Zheng1,† Yiming Li2,†
1miHoYo Honkai AI R&D Team · 2College AI, Tsinghua University 3University of Chinese Academy of Sciences · 4MMLab, The University of Hong Kong…