Function Calling on BFCL held-out V4 (test)
52.4Average ScoreCURATEEVO
Evaluation Results
| Method | Links | |
|---|---|---|
| CURATEEVOModel=QWEN3-4B, Data Setting=Labeled Data2026.07 | 52.4 | |
| FunReason-MTModel=QWEN3-4B, Data Setting=Labeled Data2026.07 | 50.3 | |
| CURATEEVOModel=QWEN3-4B, Data Setting=Wild Data2026.07 | 50 | |
| FunReason-MTModel=QWEN3-4B, Data Setting=Wild Data2026.07 | 48.7 | |
| EnvScalerModel=QWEN3-8B, Data Setting=Labeled Data2026.07 | 47.6 | |
| RODSModel=QWEN3-4B, Data Setting=Labeled Data2026.07 | 47.2 | |
| EnvScalerModel=QWEN3-8B, Data Setting=Wild Data2026.07 | 46.2 | |
| RODSModel=QWEN3-4B, Data Setting=Wild Data2026.07 | 45.9 | |
| MUA-RLModel=QWEN3-8B, Data Setting=Labeled Data2026.07 | 42.6 | |
| MUA-RLModel=QWEN3-8B, Data Setting=Wild Data2026.07 | 40.9 | |
| AWMModel=QWEN3-8B, Data Setting=Labeled Data2026.07 | 39.7 | |
| AWMModel=QWEN3-8B, Data Setting=Wild Data2026.07 | 38.4 | |
| GRPO w/o. Data CurationModel=QWEN3-8B, Data Setting=Labeled Data2026.07 | 18.7 | |
| GRPO w/o. Data CurationModel=QWEN3-8B, Data Setting=Wild Data2026.07 | 17.4 | |
| GRPO w/o. Data CurationModel=QWEN3-4B, Data Setting=Labeled Data2026.07 | 13.8 | |
| GRPO w/o. Data CurationModel=QWEN3-4B, Data Setting=Wild Data2026.07 | 12.5 |