| Benchmark | Model | Rank | Results |
|---|---|---|---|
| instruction-following-on-ifeval | SmolLM 1.7B Instruct | #14 | Prompt-level strict-accuracy: 18.48 |
| question-answering-on-piqa | SmolLM 1.7B | #89 | Accuracy: 77.3 |
| sentence-completion-on-hellaswag | SmolLM 1.7B | #134 | Accuracy: 64.1 |
| code-generation-on-humaneval | SmolLM 1.7B | #135 | Pass@1: 20.76 |
| common-sense-reasoning-on-winogrande | SmolLM 1.7B | #146 | Accuracy: 56.0 |