SmolLM2-1.7B — benchmark results
SmolLM2 1.7B base/pretrained checkpoint. Provider: HuggingFace. Released 2024-10-30. Access: Open.
Unified ELO 1245 ± 23, rank #1628 of 1776 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Fibble2 Arena | 0 | Win Rate (%) | 41.1 |
| Fibble4 Arena | 0 | Win Rate (%) | 40.5 |
| Fibble3 Arena | 0 | Win Rate (%) | 39.3 |
| Fibble5 Arena | 0 | Win Rate (%) | 36.7 |
| EuroEval Portuguese NLU - SST-2 PT | 70.07 | Sentiment classification Score (%) | 36.1 |
| Open LLM Leaderboard - GPQA | 3.91 | Score | 34.3 |
| EuroEval Spanish NLU - ScaLA ES | 1.83 | Linguistic acceptability Score (%) | 31.4 |
| EuroEval Dutch NLU - DBRD | 74.28 | Sentiment classification Score (%) | 30.1 |
| EuroEval Spanish NLU - MLQA ES | 46.34 | Reading comprehension Score (%) | 30.1 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 52.83 | Reading comprehension Score (%) | 30 |
| EuroEval Italian NLU - SQuAD IT | 45.46 | Reading comprehension Score (%) | 29.3 |
| EuroEval Icelandic Knowledge | 2.61 | Knowledge Average Score (%) | 28.9 |
Interactive version: theaggregate.ai/model?slug=smollm2-1-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.