MCP-Atlas

Measures: A model gets a single-turn request that needs several tool calls (about 3-6) across real MCP servers (36 servers, 220 tools); a task passes when the final answer covers at least 75% of the rubric's factual claims.

Maintainer: Scale AI (Scale Labs)
Introduced: 2025
Status: Active
Saturation: Near-ceiling
Typical provenance: Mixed
In scoring set: Yes

Paper Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.