openhermes-tinyllama-sft-qlora [Adapter]: benchmark results
Provider: Other.
Aggregate Rating 1152 ± 36, rank #9947 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 27.67 | Accuracy (%) (5-shot) | 15.3 |
| Open LLM Leaderboard v1 - WinoGrande | 61.56 | Accuracy (%) (5-shot) | 14.7 |
| Open LLM Leaderboard v1 - HellaSwag | 60.45 | Normalized accuracy (%) (10-shot) | 14.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 32.34 | Normalized accuracy (%) (25-shot) | 10.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 38.29 | MC2 (%) (0-shot) | 7.8 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
Interactive version: theaggregate.ai/model?slug=openhermes-tinyllama-sft-qlora-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.