DollyEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Instruction Following | DollyEval | Rouge-L32.5 | 114 | |
| Instruction following | DollyEval 500 (test) | Rouge-L31.3 | 24 | |
| Dialogue Generation | DollyEval | ROUGE-L24.19 | 16 | |
| Generation | DollyEval (test) | LLM-as-a-Judge Score62.02 | 2 | |
| Instruction Following | DollyEval (test) | Score- | 0 |
Showing 5 of 5 rows