Human A/B
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Helpful response generation | Human A/B 100 randomly chosen instances (test) | Human Preference Score62 | 2 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Helpful response generation | Human A/B 100 randomly chosen instances (test) | Human Preference Score62 | 2 |