Benchmark
MCP-Mark Benchmark
What is MCP-Mark?
MCP-Mark evaluates LLMs on their ability to use Model Context Protocol (MCP) tools effectively, testing tool discovery, selection, invocation, and result…
- Modality
- text
- Evaluates
- agents, tool calling
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 8
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mcp-mark?top_n=500
MCP-Mark results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-V3.2 | DeepSeek | 0.38 | 2025-12-01 | evidence |
| Kimi K2.6 | Moonshot AI | 0.559 | 2026-04-20 | evidence |
| Kimi K2.7 Code | Moonshot AI | 0.811 | 2026-06-12 | evidence |
| Qwen3.5-397B-A17B | Qwen | 0.461 | 2026-02-16 | evidence |
| Qwen3.6 Plus | Qwen | 0.482 | 2026-04-02 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.37 | 2026-04-16 | evidence |
| Qwen3.7 Max | Qwen | 0.608 | 2026-05-19 | evidence |
| Qwen3.7-Plus | Qwen | 0.587 | 2026-05-31 | 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.