VicunaEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Instruction Following | VicunaEval | VicunaEval Score40.75 | 80 | |
| Instruction Following | VicunaEval | Rouge-L35 | 72 | |
| General Performance | VicunaEval | Winrate96.3 | 21 | |
| Generation | VicunaEval (test) | LLM Judge Score56.07 | 2 | |
| Instruction Following | VicunaEval (test) | Score- | 0 |
Showing 5 of 5 rows