Features
Two-stage scoring: HTTP interception + LLM judge
283 live tasks across 163 live platforms
Public leaderboard with cost/task metrics
Multiple evaluation harnesses (Claw-Eval, WildClawBench, ClawMark)
Open-source dataset and traces on Hugging Face
CLI tool: pip install clawbench-eval
Supports V1 and V2 corpora
Scoring rubrics: lenient and strict reward
Gradio Space for interactive leaderboard browsing
Model submission and comparison support
Task gallery and trace visualization
Integration with other benchmarks (WebVoyager, OSWorld)
5-layer trace bundles with video, HAR, agent reasoning
JSONL-native dataset for SFT/DPO/PRM-ready fine-tuning
Weekly refreshed traces with 283+ tasks
Access 100+ data providers for firmographics, technographics, funding
Live intent signals: job changes, funding, hiring, website visits
AI research agents for deep company and competitor analysis
Built-in AI sequencer for multi-channel outreach with warmup
Native email sending with automated warmup
Lead scoring based on propensity to buy
Local business search from Google Maps with import
Enriched LinkedIn posts, company details, and mobile numbers
HTTP API and webhooks for custom integrations
CRM sync with HubSpot and Salesforce (Pro+)
Credit-based system: 1 credit per email, 10 credits per phone
Unlimited users on all paid plans
Web scrapers for custom data extraction
Company Lookalike Finder (Growth+)
ABM (Account-Based Marketing) on Pro+
