VGenST-Bench

What is VGenST-Bench?

VGenST-Bench evaluates spatio-temporal reasoning in multimodal large language models using 1,200 procedurally generated videos with controlled scene…

Released

2026-05-21

Evaluates

General AI, Reasoning, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.22570

VGenST-Bench paper and code

• Paper https://arxiv.org/abs/2605.22570
• Code https://github.com/zinosii/VGenST-Bench
• Website https://zinosii.github.io/VGenST-Bench/

Which sources cite VGenST-Bench?

• VGenST-Bench

Related General AI, Reasoning, Vision & 3D benchmarks

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