K-BrowseComp Benchmark

What is K-BrowseComp?

K-BrowseComp evaluates web-browsing agents on 400 Korean-context problems, requiring multi-hop or parallel evidence retrieval from public Korean websites and…

Released

2026-06-01

Evaluates

Agents, Cybersecurity, Language & Knowledge

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.02404

K-BrowseComp paper and code

• Paper https://arxiv.org/abs/2606.02404
• Code https://github.com/prometheus-eval/K-BrowseComp

Which sources cite K-BrowseComp?

• K-BrowseComp

Related Agents, Cybersecurity, Language & Knowledge benchmarks

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