Developer
Fudan NLP
4 indexed models; 1 currently meet the evidence threshold for the overall ranking. Together they have results from 6 evaluations.
Models by Fudan NLP
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Moss Moon 003 Sft | 3 | 3/7 | 242 | 2023-04-19 |
| Moss | 1 | 1/7 | — | 2023-04-19 |
| Moss 16B | 1 | 3/7 | — | 2023-04-19 |
| Moss Sft 16B | 1 | 1/7 | — | — |
Evaluations covering Fudan NLP models (6)
Chinese Bias Benchmark for Question Answering · CMoralEval · CValues · Fake Alignment (FINE) · FLAMES · SuperCLUE Safety