EQ-Bench and LongBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human Preference Evaluation | EQ-Bench Creative and LongBench Write (60 pairs) | Winrate67.5 | 2 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human Preference Evaluation | EQ-Bench Creative and LongBench Write (60 pairs) | Winrate67.5 | 2 |