smol_llama-220M-openhermes: benchmark results
BEE-spoke-data release: An instruction fine-tune of smol_llama-220M-GQA using teknium/openhermes, with an Alpaca-style instruction/input/response format. Provider: BEE-spoke-data. Access: Open.
Aggregate Rating 1106 ± 35, rank #10649 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 38.47 | Score | 32.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.08 | MC2 (%) (0-shot) | 22.5 |
| Open LLM Leaderboard - GPQA | 26.76 | Score | 22 |
| Open LLM Leaderboard v1 - GSM8K | 0.61 | Accuracy (%) (5-shot) | 13.1 |
| Open LLM Leaderboard v1 - MMLU | 26.17 | Accuracy (%) (5-shot) | 11.6 |
| Open LLM Leaderboard - MATH Level 5 | 1.06 | Score | 7.6 |
| Open LLM Leaderboard v1 - WinoGrande | 52.01 | Accuracy (%) (5-shot) | 6.3 |
| Open LLM Leaderboard - BBH | 30.28 | Score | 5.7 |
| Open LLM Leaderboard - IFEval | 15.55 | Score | 5.7 |
| Open LLM Leaderboard v1 - HellaSwag | 28.98 | Normalized accuracy (%) (10-shot) | 5 |
| Open LLM Leaderboard v1 - ARC Challenge | 25.17 | Normalized accuracy (%) (25-shot) | 4.5 |
| Open LLM Leaderboard - MMLU-Pro | 11.2 | Score | 3.3 |
Interactive version: theaggregate.ai/model?slug=smol-llama-220m-openhermes · How It Works · Data refreshed daily, snapshot 2026-11-08.