Loading benchmark results... 01 Open-Meteo Weather API open-meteo.com 100% passed Open-Meteo agent profile: Install S, Auth S, Execute S, Docs S, Current S 100 Agent-Ready — 02 context.dev Search context.dev 100% passed context.dev agent profile: Install S, Auth S, Execute S, Docs S, Current S 100 Agent-Ready — 03 Firecrawl Search firecrawl.dev 100% passed Firecrawl agent profile: Install S, Auth S, Execute S, Docs S, Current S 100 Agent-Ready — 04 Parallel Search parallel.ai 75% passed · 1 blocked 75% 3 of 4 passed · 1 blocked
Parallel agent profile: Install S, Auth S, Execute S, Docs S, Current S 100 Agent-Ready — 05 tinyfish.ai Browser Automation tinyfish.ai 67% passed · 1 blocked 67% 2 of 3 passed · 1 blocked
tinyfish.ai agent profile: Install S, Auth S, Execute S, Docs S, Current S 100 Agent-Ready — 06 duckdb.org Embedded analytical database duckdb.org/docs/current 100% passed duckdb.org agent profile: Install A, Auth S, Execute S, Docs S, Current S 98 Agent-Ready — 07 Exa Search exa.ai 89% passed · 1 blocked 89% 8 of 9 passed · 1 blocked
Exa agent profile: Install S, Auth A, Execute A, Docs S, Current S 84 Needs Alignment — 08 Tavily Search docs.tavily.com/documentation/quickstart 0% passed · 2 blocked 0% 0 of 2 passed · 2 blocked
Tavily agent profile: Install A, Auth A, Execute D, Docs A, Current S 46 Critical Gating — 09 struct.ai AI production monitoring struct.ai 0% passed · 1 blocked 0% 0 of 1 passed · 1 blocked
struct.ai agent profile: Install D, Auth C, Execute D, Docs S, Current A 26 Critical Gating — 10 apollo.io Sales intelligence apollo.io 0% passed · 2 blocked 0% 0 of 2 passed · 2 blocked
Not graded — 11 AI SDK AI SDK ai-sdk.dev 0% passed · 1 blocked 0% 0 of 1 passed · 1 blocked
Not graded — 12 Stripe Payments stripe.com 0% passed · 1 blocked 0% 0 of 1 passed · 1 blocked
Not graded — 13 tinyfish.com Browser Automation tinyfish.com 0% passed · 1 blocked 0% 0 of 1 passed · 1 blocked
Not graded — 