Tool Calling on BFCL V3
70.4pass@1Qwen3 14B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3 14BParameters=14B2025.12 | 70.4 | |
| Gemini-2.5 Flash-ThinkingThinking Mode=true2025.12 | 68.6 | |
| Qwen3 8BParameters=8B2025.12 | 68.1 | |
| DeepSeek-R1 0528 671BParameters=671B, Thinking Mode=true2025.12 | 67.9 | |
| Nemotron-Cascade 14B-ThinkingParameters=14B, Thinking Mode=true2025.12 | 67.5 | |
| Nemotron-Nano 9B-v2Parameters=9B-v22025.12 | 66.9 | |
| Nemotron Cascade-8BParameters=8B, Thinking Mode=true2025.12 | 64.4 |