SmolLM-360M-Instruct: benchmark results
Hugging Face's SmolLM-360M-Instruct, fine-tuned from the SmolLM-360M 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 1186 ± 37, rank #1597 of 1656 rated models, from 45 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Bias Risk | 23.77 | Risk Score | 99 |
| Enkrypt AI - Safety Risk | 34.26 | Risk Score | 25.9 |
| Enkrypt AI - Jailbreak Risk | 15.73 | Risk Score | 24.8 |
| Enkrypt AI - Risk Score | 41.52 | Risk Score | 18.9 |
| Open LLM Leaderboard - GPQA | 26.43 | Score | 18.3 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 15.38 | Macro F1 (%) | 16.9 |
| Open PL LLM - PSC (generative, 5-shot) | 62.91 | Binary F1 (%) | 16.3 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 38.87 | Accuracy (%) | 16.1 |
| Enkrypt AI - Toxicity Risk | 10 | Risk Score | 15 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 23.86 | Accuracy (%) | 13.3 |
| Open LLM Leaderboard - MATH Level 5 | 1.81 | Score | 12.8 |
| Open PL LLM - CBD (generative, 5-shot) | 15.12 | Macro F1 (%) | 12.3 |
Interactive version: theaggregate.ai/model?slug=smollm-360m-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.