OR-Bench

What is OR-Bench?

Vision-language models (VLMs) can detect that an object has rotated across views, but cannot reliably tell by how much.

Released

2026-10-05

Evaluates

General AI, Reasoning, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2610.05715

OR-Bench paper

• Paper https://arxiv.org/abs/2610.05715

Which sources cite OR-Bench?

• OR-Bench

Related General AI, Reasoning, Vision & 3D benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A-OKVQA
• A3S-Bench
• AARRI-Bench