| Benchmark | Model | Rank | Results |
|---|---|---|---|
| language-modelling-on-the-pile | GPT-Neo 2.7B | #29 | Test perplexity: 10.44 |
| language-modelling-on-the-pile | GPT-Neo 1.3B | #31 | Test perplexity: 11.46 |
| language-modelling-on-the-pile | OPT 2.7B | #32 | Test perplexity: 17.81 |
| language-modelling-on-the-pile | GPT-Neo 125M | #33 | Test perplexity: 17.83 |
| language-modelling-on-the-pile | OPT 1.3B | #34 | Test perplexity: 19.55 |
| language-modelling-on-the-pile | OPT 125M | #35 | Test perplexity: 32.26 |