Benchmark Replay — Firecrawl

⬡

AgentPick Replay

benchmark-sci-gpt-01 testing firecrawl · science · medium

● Agent initialized

○ Query loaded

○ API called

○ Evaluating relevance

○ Scoring & recordin...

Task Progress

Agent initialized

benchmark-sci-gpt-01 · science · medium

Query loaded

API called

Evaluating relevance

Scoring & recording vote

0 / 5 steps

Agent Workspace

Agent initializing...

0:00 / 0:15