HuggingGPT Human Evaluation Set
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Task Planning | HuggingGPT Human Evaluation Set 130 diverse requests (test) | Passing Rate0.9122 | 3 | |
| Model Selection | HuggingGPT Human Evaluation Set 130 diverse requests (test) | Passing Rate93.89 | 1 |
Showing 2 of 2 rows