MCP Atlas — leaderboard
Evaluating real-world tool use through the Model Context Protocol (MCP).
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 32 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 83.6 |
| 2 | Claude Fable 5 | 83.3 |
| 3 | Muse Spark | 82.2 |
| 4 | Claude Opus 4.7 | 79.1 |
| 5 | Gemini 3.1 Pro (Preview) (High) | 78.2 |
| 6 | Claude Opus 4.8 | 77.8 |
| 7 | GLM-5.2 | 76.8 |
| 8 | Claude Opus 4.6 (Max) | 76.8 |
| 9 | Qwen 3.7 Max (Max) | 76.4 |
| 10 | Kimi K2.7 Code | 76 |
| 11 | GLM-5.1 | 75.6 |
| 12 | GPT-5.5 (xHigh) | 75.3 |
| 13 | MiniMax-M3 | 74.2 |
| 14 | Qwen 3.6 Plus | 74.1 |
| 15 | DeepSeek V4 Pro | 73.6 |
Interactive version: theaggregate.ai/benchmark?slug=mcp-atlas · How the rankings work · Data refreshed daily, snapshot 2026-07-22.