Benchmark
MCP Atlas
Public and full splits are both reported under one name; the tool server set is part of the measurement.
- Released
- 2025-11-18
- Categories
- tool_use
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 8
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-V4-Flash | DeepSeek | 69.0 | 2026-06-25 | evidence |
| DeepSeek-V4-Pro | DeepSeek | 73.6 | 2026-04-22 | evidence |
| Gemini 3.1 Pro | 69.2 | 2026-02-19 | evidence | |
| GLM-5 | Z.ai | 67.8 | 2026-02-11 | evidence |
| GLM-5.1 | Z.ai | 71.8 | 2026-04-03 | evidence |
| GLM-5.2 | Z.ai | 76.8 | 2026-06-16 | evidence |
| Hy4 preview | Tencent | 83.7 | 2026-08-28 | evidence |
| Kimi K3 | Moonshot AI | 84.2 | 2026-06-13 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.