Trajectory Planning On Toolbench
评估指标
Win rate
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Win rate |
|---|---|
| fortify-the-shortest-stave-in-attention | 71.5 |
| swissnyf-tool-grounded-llm-agents-for-black | 86.54 |
| toolllm-facilitating-large-language-models-to | 70.4 |
各个模型在此基准测试上的表现结果
| 模型名称 | Win rate |
|---|---|
| fortify-the-shortest-stave-in-attention | 71.5 |
| swissnyf-tool-grounded-llm-agents-for-black | 86.54 |
| toolllm-facilitating-large-language-models-to | 70.4 |