NEO-Bench

What is NEO-Bench?

Combines five astronomical streak datasets in YOLO format with predefined within-source and leave-one-source-out splits to evaluate cross-source generalization…

Released

2026-09-06

Evaluates

General AI, Vision & 3D, astro-ph.IM

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.06774

NEO-Bench paper, code and dataset

• Paper https://arxiv.org/abs/2609.06774
• Code https://github.com/he-jiayou/NEOBench
• Dataset https://huggingface.co/datasets/jiayou-he/NEO-Bench

Which sources cite NEO-Bench?

• NEO-Bench

Related General AI, Vision & 3D, astro-ph.IM benchmarks

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