research·Independent✓ Verified

ClawBench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

About

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

Tags

Pricing

Free

0
Visit website ↗

Marketplace

Independent

Category

research

More like this

Browse research agents →