Tool-use on ToolQuery
73.3Success RateMAGNET-14B-mDPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAGNET-14B-mDPOModel size=14B, Training=mDPO2025.03 | 73.3 | 78.7 | |
| Gemini-1.5 pro 002Model version=1.5 pro 0022025.03 | 68.3 | 74.6 | |
| xLAM-8x22b-rModel size=8x22b-r2025.03 | 68.3 | 75.8 | |
| MAGNET-7B-mDPOModel size=7B, Training=mDPO2025.03 | 67.7 | 73.4 | |
| GPT-4o2025.03 | 63.3 | 80.1 | |
| Qwen-Coder-14B-instructModel size=14B, Mode=instruct2025.03 | 51.7 | 68.7 | |
| Qwen-Coder-7B-instructModel size=7B, Mode=instruct2025.03 | 15 | 34 |