Scarlett-Llama-3-8B: benchmark results
A full Llama-3-8B fine-tune by ajibawa-2023 on over 10,000 conversation sets covering philosophy, advice, jokes and coding. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1423 ± 33, rank #5038 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.46 | Accuracy (%) (5-shot) | 87.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.27 | MC2 (%) (0-shot) | 67.5 |
| Open LLM Leaderboard v1 - HellaSwag | 83.86 | Normalized accuracy (%) (10-shot) | 62.1 |
| Open LLM Leaderboard v1 - GSM8K | 47.31 | Accuracy (%) (5-shot) | 60.7 |
| Open LLM Leaderboard v1 - WinoGrande | 78.06 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
Interactive version: theaggregate.ai/model?slug=scarlett-llama-3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.