Llama 3 8B Spaetzle V33: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1450 ± 33, rank #3779 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 68.37 | Accuracy (%) (5-shot) | 91.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.03 | Normalized accuracy (%) (25-shot) | 82 |
| Open LLM Leaderboard v1 - GSM8K | 65.28 | Accuracy (%) (5-shot) | 79.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.28 | MC2 (%) (0-shot) | 73.5 |
| Open LLM Leaderboard v1 - HellaSwag | 84.64 | Normalized accuracy (%) (10-shot) | 67.5 |
| Open LLM Leaderboard v1 - WinoGrande | 78.37 | Accuracy (%) (5-shot) | 62.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-spaetzle-v33 · How It Works · Data refreshed daily, snapshot 2026-11-08.