Updated daily at 05:00 UTC
Benchmark
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
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results