Llama 3 8B Cumulus V0.1: benchmark results
Provider: Meta.
Aggregate Rating 1389 ± 35, rank #6540 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 60.8 | Accuracy (%) (5-shot) | 73 |
| Open LLM Leaderboard v1 - MMLU | 62.59 | Accuracy (%) (5-shot) | 55.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.98 | MC2 (%) (0-shot) | 50.2 |
| Open LLM Leaderboard v1 - WinoGrande | 76.4 | Accuracy (%) (5-shot) | 48 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.03 | Normalized accuracy (%) (25-shot) | 32.5 |
| Open LLM Leaderboard v1 - HellaSwag | 77.55 | Normalized accuracy (%) (10-shot) | 31.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-cumulus-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.