SlimOrca-Llama-3-8B: benchmark results
A full Llama-3 fine-tune by ajibawa-2023 on 517,981 conversation sets derived from Open-Orca/SlimOrca and repackaged as SlimOrca-ShareGPT. Dataset authorship remains credited to Open-Orca. Provider: ajibawa-2023. Access: Open.
Aggregate Rating 1326 ± 34, rank #8229 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 36.77 | Accuracy (%) (5-shot) | 52.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.03 | MC2 (%) (0-shot) | 39.6 |
| Open LLM Leaderboard v1 - MMLU | 53.12 | Accuracy (%) (5-shot) | 32.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.77 | Normalized accuracy (%) (25-shot) | 25.1 |
| Open LLM Leaderboard v1 - WinoGrande | 68.75 | Accuracy (%) (5-shot) | 22.8 |
| Open LLM Leaderboard v1 - HellaSwag | 71.51 | Normalized accuracy (%) (10-shot) | 21.6 |
Interactive version: theaggregate.ai/model?slug=slimorca-llama-3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.