SmolLM-1.7B-Instruct: benchmark results
Hugging Face's SmolLM-1.7B-Instruct, fine-tuned from the SmolLM-1.7B base model on public instruction datasets, part of the three-size SmolLM family trained on curated educational and synthetic data. Provider: HuggingFace. Released 2024-07-16. Access: Open.
Aggregate Rating 1197 ± 32, rank #1583 of 1656 rated models, from 51 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open CoT - LSAT Analytical Reasoning | 1.74 | CoT Gain (%) | 24.8 |
| Open PL LLM - CBD (generative, 5-shot) | 16.32 | Macro F1 (%) | 23 |
| Open Portuguese LLM - ASSIN2 RTE | 59.53 | Macro F1 (%) | 20.8 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 35.51 | Binary F1 (%) | 20.1 |
| Open PL LLM - PSC (generative, 5-shot) | 68.44 | Binary F1 (%) | 18.8 |
| Open LLM Leaderboard - IFEval | 23.48 | Score | 17 |
| Open PL LLM - KLEJ NER (generative, 5-shot) | 29.35 | Accuracy (%) | 15.7 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 38.06 | Accuracy (%) | 15.5 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 20.43 | Binary F1 (%) | 15.4 |
| Open LLM Leaderboard - MATH Level 5 | 2.11 | Score | 14.7 |
| Open CoT - LSAT Reading Comprehension | 3.35 | CoT Gain (%) | 14.5 |
| Enkrypt AI - Jailbreak Risk | 24.54 | Risk Score | 13.9 |
Interactive version: theaggregate.ai/model?slug=smollm-1-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.