BrowseComp-ZH

Chinese web-browsing research benchmark.

BrowseComp-ZH evaluates Chinese web-browsing and research ability with judge-scored questions.

Runtime Status

Field	Value
Benchmark id	browsecomp_zh
Tags	Deep Research, Web Browsing, Chinese, Judge-Scored
Execution type	local with judge
Typical harness	researchharness or naive_search_agent
Typical environment	host_process
Current status	registered in the direct runtime

Run Example

agentcompass run \
  browsecomp_zh \
  researchharness \
  your-model \
  --env <env-provider> \
  --benchmark-params '{"sample_ids":["<task-id>"]}' \
  --model-base-url "$MODEL_BASE_URL" \
  --model-api-key "$MODEL_API_KEY"

Use judge_model in --benchmark-params when the run config does not already provide one.

Outputs

Per-task details are written to results/browsecomp_zh/<model>/<run>/details/. Aggregate metrics are written to summary.md.