SmolLM3-3B — benchmark results
Hugging Face's fully open Apache-2.0 3B model (July 2025) with dual think/no-think reasoning modes, 128K context, and a published training recipe and data mix. Provider: HuggingFace. Released 2025-07-01. Access: Open.
Unified ELO 1410 ± 14, rank #1172 of 1776 rated models, from 150 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - COPA Spanish | 84.2 | Accuracy (%) | 83.1 |
| AI Energy Score (Text Generation) | 5 | Energy Score (1-5) | 79.5 |
| LA Leaderboard - GalCoLA | 55.12 | Accuracy (%) | 79.4 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 73.09 | Reading comprehension Score (%) | 74.7 |
| EuroEval Portuguese NLU - ScaLA PT | 21.3 | Linguistic acceptability Score (%) | 72.5 |
| EuroEval German NLU - Germanquad | 56.07 | Reading comprehension Score (%) | 70.9 |
| EuroEval Portuguese NLU | 54.22 | NLU Average Score (%) | 70.7 |
| LA Leaderboard | 55.64 | Average Score (%) | 69.9 |
| EuroEval Spanish NLU - MLQA ES | 62.91 | Reading comprehension Score (%) | 69.2 |
| EuroEval Portuguese NLU - SST-2 PT | 79.85 | Sentiment classification Score (%) | 64.5 |
| EuroEval French NLU - FQuAD | 67.79 | Reading comprehension Score (%) | 64.1 |
| EuroEval Spanish NLU - ScaLA ES | 23.42 | Linguistic acceptability Score (%) | 62.3 |
Interactive version: theaggregate.ai/model?slug=smollm3-3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.