Tool Use Evaluation on GTM
89.4Average ScoreGTM-1.5B
Evaluation Results
| Method | Links | |
|---|---|---|
| GTM-1.5BModel Size=1.5B2025.12 | 89.4 | |
| Qwen2.5-14B-InstructModel Size=14B2025.12 | 85.8 | |
| Qwen2.5-7B-InstructModel Size=7B2025.12 | 83 | |
| InternLM2.5-20BModel Size=20B2025.12 | 69.4 | |
| Llama-3.2-3B-InstructModel Size=3B2025.12 | 68.3 | |
| Qwen2.5-3B-InstructModel Size=3B2025.12 | 65.3 | |
| Qwen2.5-1.5B-InstructModel Size=1.5B2025.12 | 61.2 | |
| Qwen2.5-0.5B-InstructModel Size=0.5B2025.12 | 45.1 | |
| Llama-3.2-1B-InstructModel Size=1B2025.12 | 39.8 | |
| InternLM2.5-7BModel Size=7B2025.12 | 39.2 | |
| InternLM2.5-1.8BModel Size=1.8B2025.12 | 10.8 |