New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
MCP-Universe benchmark
AI model leaderboard for the MCP-Universe benchmark. Compare how large language models score on MCP-Universe, see the full ranking, and understand what this AI benchmark measures. Gemini 3 Pro currently leads with 50.7. Agentic benchmark spanning Model Context Protocol tool use across heterogeneous MCP servers.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Gemini 3 Pro | Google DeepMind | 50.7 | cited-deepseek-v3-2 | official ↗ |
| #2 | GPT-5 | OpenAI | 47.9 | cited-deepseek-v3-2 | official ↗ |
| #3 | Claude Sonnet 4.5 | Anthropic | 46.5 | cited-deepseek-v3-2 | official ↗ |
| #4 | DeepSeek-V3.2 | DeepSeek | 45.9 | thinking | official ↗ |
| #5 | Kimi K2 Thinking | Moonshot | 35.6 | thinking-cited-deepseek-v3-2 | official ↗ |
| #6 | MiniMax-M2 | MiniMax | 29.4 | cited-deepseek-v3-2 | official ↗ |
Frequently asked questions about MCP-Universe
What is the MCP-Universe benchmark?
Agentic benchmark spanning Model Context Protocol tool use across heterogeneous MCP servers.
How is the MCP-Universe benchmark scored?
MCP-Universe is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on MCP-Universe?
As of the latest reported scores on GenAIList, Gemini 3 Pro achieves the highest result on MCP-Universe with a score of 50.7.
Is a higher MCP-Universe score better?
Yes. On MCP-Universe a higher score indicates better performance, so models near the top of the leaderboard are the strongest.