Function Calling on BFCL Parallel-Multiple (AUROC)
76AUROCG-NLL
Evaluation results
| Method | Links | |
|---|---|---|
| G-NLLSampling Strategy=Single-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 76 | |
| AVGSampling Strategy=Single-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 74 | |
| SEEXMSampling Strategy=Multi-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 73 | |
| DSEEXMSampling Strategy=Multi-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 73 | |
| MAXSampling Strategy=Single-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 72 | |
| PESampling Strategy=Multi-sample, Model Aggregation=Mean over 8 LLMs2026.04 | 72 | |
| PtrueSampling Strategy=Other, Model Aggregation=Mean over 8 LLMs2026.04 | 67 | |
| LENSampling Strategy=Other, Model Aggregation=Mean over 8 LLMs2026.04 | 55 |