EgoSAT Benchmark

What is EgoSAT?

EgoSAT evaluates vision-language models on egocentric video reasoning in streaming settings. It contains 1,997 videos (165 hours) and about 4,800 QA pairs…

Released

2026-06-23

Evaluates

General AI, Multimodal, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.24422

EgoSAT paper

• Paper https://arxiv.org/abs/2606.24422
• Website https://leiyj23.github.io/EgoSAT/

Which sources cite EgoSAT?

• EgoSAT

Related General AI, Multimodal, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench