K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
This benchmark fills the gap in Korean agentic evaluations, revealing a substantial performance drop for both frontier and Korean-specific models.
K-BrowseComp introduces a 400-problem web-browsing agent benchmark grounded in Korean contexts, with a 300-problem verified subset where frontier LLMs achieve only 30.00–45.67% accuracy, far below their performance on English benchmarks, and Korean LLMs score 0.00–10.33%.
Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks remain scarce. We introduce K-BrowseComp, a web-browsing agent benchmark grounded in Korean contexts, consisting of 400 problems. The 300-problem K-BrowseComp-Verified subset is manually constructed and validated by native Korean speakers. On this subset, frontier LLMs, including GPT-5.5, DeepSeek-V4-Pro, and GLM-5.1, reach only 30.00--45.67\%, a substantial drop from BrowseComp, while Korean LLMs released through Korea's Proprietary AI Foundation Model program obtain only 0.00--10.33\%. We further construct a 100-problem synthetic split using hard few-shot exemplars and failure-mode-targeted generation to exploit the asymmetry between solving and creating web browsing problems. On the adversarially filtered synthetic diagnostic split, the strongest model reaches only 26.00\%, and we report this split separately as a targeted stress test. We publicly release our data and code.