diff --git a/README.md b/README.md index 7b5d3b0..380e352 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,7 @@ Together they make external results easy to run, compare, cite, and submit back. - `All` (300) / `Hard` (hard subset) - [x] **BrowseComp** — Browser operation competition tasks, no login required - `All` (1266) +- [ ] **ClawBench** — Open web-agent benchmark with 283 V1+V2 tasks across 163 live websites, using submission interception and judge-based outcome evidence - [ ] More benchmarks > Details: [Benchmarks overview](https://docs.bubench.lexmount.io/en/benchmarks/overview).