Skip to content
ClawBench
  • Home
  • Tasks
  • Gallery
  • Traces
  • Compare
  • Contribute
arXiv HF Dataset HF Traces HF Papers GitHub

ClawBench is an open benchmark that measures whether AI browser agents can complete everyday online tasks on live websites. The V2 corpus has 130 tasks across 63 platforms in 30 task categories, and the V1 corpus has 153 tasks. Each run is scored in two stages: the agent's final HTTP request is intercepted and matched to the task schema, then an LLM judge checks the payload against the instruction. On V2 (hermes harness), claude-opus-4-7 leads with 71 of 130 runs intercepted (54.6%) and a 44.6% reward rate; on V1, claude-opus-4-6 leads with 94 of 153 (61.4%). Leaderboard data as of 2026-05-20.

Home Tasks Gallery Traces Compare Contribute
ClawBench © 2026 · Agent Benchmark · Contribute · Contact