Repository Management on MCP-Universe Repository Management
45.45Success RateToolGate
Evaluation Results
| Method | Links | |
|---|---|---|
| ToolGateModel=GPT-5.22026.01 | 45.45 | |
| ToolGateModel=Gemini 3 Pro2026.01 | 42.42 | |
| ToolChain*Model=GPT-5.22026.01 | 39.39 | |
| LATSModel=GPT-5.22026.01 | 36.36 | |
| ToolChain*Model=Gemini 3 Pro2026.01 | 36.36 | |
| LATSModel=Gemini 3 Pro2026.01 | 33.33 | |
| Tool-PlannerModel=GPT-5.22026.01 | 30.3 | |
| DFSDTModel=GPT-5.22026.01 | 27.27 | |
| Tool-PlannerModel=Gemini 3 Pro2026.01 | 27.27 | |
| ToolGateModel=Deepseek V3.22026.01 | 24.24 | |
| ReACTModel=GPT-5.22026.01 | 24.24 | |
| DFSDTModel=Gemini 3 Pro2026.01 | 24.24 | |
| ToolGateModel=Qwen-3-235B2026.01 | 21.21 | |
| ToolChain*Model=Deepseek V3.22026.01 | 21.21 | |
| ReACTModel=Gemini 3 Pro2026.01 | 21.21 | |
| ToolChain*Model=Qwen-3-235B2026.01 | 18.18 | |
| LATSModel=Deepseek V3.22026.01 | 18.18 | |
| LATSModel=Qwen-3-235B2026.01 | 15.15 | |
| DFSDTModel=Deepseek V3.22026.01 | 15.15 | |
| Tool-PlannerModel=Deepseek V3.22026.01 | 15.15 | |
| DFSDTModel=Qwen-3-235B2026.01 | 12.12 | |
| Tool-PlannerModel=Qwen-3-235B2026.01 | 12.12 | |
| ReACTModel=Deepseek V3.22026.01 | 12.12 | |
| ReACTModel=Qwen-3-235B2026.01 | 9.09 |