AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
MCP Atlas
Public and full splits are both reported under one name; the tool server set is part of the measurement.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2025-11-18
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 8
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| DeepSeek-V4-Pro | 73.6 | percent | think max, pass@1 | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Flash | 69.0 | percent | think max, pass@1 | 2026-06-25 · document_publication | DeepSeek-V4 |
| Gemini 3.1 Pro | 69.2 | percent | Thinking (High) | 2026-02-19 · document_publication | Gemini 3.1 Pro |
| Kimi K3 | 84.2 | percent | reasoning=max | 2026-06-13 · document_publication | Kimi K3 |
| Hy4 preview | 83.7 | percent | as printed in the report's benchmark table | 2026-08-28 · document_publication | Hy4 preview |
| GLM-5.1 | 71.8 | percent | as reported | 2026-04-03 · document_publication | GLM-5.1 |
| GLM-5.2 | 76.8 | percent | think mode, 500-task public subset, 10-min timeout, Gemini-3.0-Pro judge | 2026-06-16 · document_publication | GLM-5.2 |
| GLM-5 | 67.8 | percent | think mode, 500-task public subset, 10-min timeout, Gemini 3 Pro judge | 2026-02-11 · document_publication | GLM-5 |