Llama 3 8B Spaetzle V20: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1455 ± 34, rank #3524 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 68.52 | Accuracy (%) (5-shot) | 91.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.39 | Normalized accuracy (%) (25-shot) | 85.8 |
| Open LLM Leaderboard v1 - GSM8K | 67.02 | Accuracy (%) (5-shot) | 82.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.98 | MC2 (%) (0-shot) | 76.8 |
| Open LLM Leaderboard v1 - HellaSwag | 85.69 | Normalized accuracy (%) (10-shot) | 76.1 |
| Open LLM Leaderboard v1 - WinoGrande | 78.37 | Accuracy (%) (5-shot) | 62.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-spaetzle-v20 · How It Works · Data refreshed daily, snapshot 2026-11-08.