Tool selection on SD Single-domain
94.04AccuracyMTA
Evaluation Results
| Method | Links | |
|---|---|---|
| MTABackbone=Qwen1.5-Chat (7B)2026.01 | 94.04 | |
| FTBackbone=Qwen1.5-Chat (7B)2026.01 | 92.31 | |
| MTABackbone=Baichuan2-Chat (7B)2026.01 | 92 | |
| FTBackbone=Baichuan2-Chat (7B)2026.01 | 88.49 | |
| MTABackbone=Chinese Alpaca-2 (7B)2026.01 | 87.92 | |
| MTABackbone=ChatGLM3 (6B)2026.01 | 83.68 | |
| FTBackbone=Chinese Alpaca-2 (7B)2026.01 | 81.98 | |
| FTBackbone=ChatGLM3 (6B)2026.01 | 78.68 | |
| ReActBackbone=Qwen1.5-Chat (7B)2026.01 | 46.82 | |
| ReActBackbone=ChatGLM3 (6B)2026.01 | 40.68 | |
| BaseBackbone=Qwen1.5-Chat (7B)2026.01 | 37.74 | |
| ReActBackbone=Baichuan2-Chat (7B)2026.01 | 37.36 | |
| CoTBackbone=Qwen1.5-Chat (7B)2026.01 | 36.82 | |
| CoTBackbone=ChatGLM3 (6B)2026.01 | 36.27 | |
| BaseBackbone=ChatGLM3 (6B)2026.01 | 35.35 | |
| BaseBackbone=Baichuan2-Chat (7B)2026.01 | 34.2 | |
| BaseBackbone=Chinese Alpaca-2 (7B)2026.01 | 28.7 | |
| CoTBackbone=Baichuan2-Chat (7B)2026.01 | 27.19 | |
| ReActBackbone=Chinese Alpaca-2 (7B)2026.01 | 21.11 | |
| CoTBackbone=Chinese Alpaca-2 (7B)2026.01 | 21.06 |