LiveBrowseComp Benchmark

What is LiveBrowseComp?

A deep-search evaluation containing 335 human-authored questions about recently published, non-globally-salient facts.

Released

2026-05-27

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.28721

LiveBrowseComp paper and dataset

• Paper https://arxiv.org/abs/2605.28721
• Dataset https://huggingface.co/datasets/Forival/LiveBrowseComp

Which sources cite LiveBrowseComp?

• LiveBrowseComp

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench