| Benchmark | Model | Rank | Results |
|---|---|---|---|
| zero-shot-question-answering-on-openbookqa | Falcon-1A.2130M | #21 | Accuracy: 33.2 |
| language-modelling-on-lambada | Falcon-1A.1130M | #79 | Perplexity: 47.93 |
| question-answering-on-piqa | Falcon-1A.2130M | #152 | Accuracy: 67.03 |
| common-sense-reasoning-on-winogrande | Falcon-1A.2130M | #156 | Accuracy: 52.96 |
| sentence-completion-on-hellaswag | Falcon-1.3130M | #205 | Accuracy: 38.38 |