Tool Use on MCP-Universe
50.7Success RateGemini-3.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3.0 Proenvironment=internal2025.12 | 50.7 | |
| GPT-5 Highenvironment=internal2025.12 | 47.9 | |
| Claude-4.5-Sonnetenvironment=internal2025.12 | 46.5 | |
| DeepSeek-V3.2environment=internal, thinking mode=true2025.12 | 45.9 | |
| Kimi-K2environment=internal, thinking mode=true2025.12 | 35.6 | |
| MiniMax M2environment=internal2025.12 | 29.4 |