llama-pile-350B: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1134 ± 34, rank #10243 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 0.76 | Accuracy (%) (5-shot) | 14 |
| Open LLM Leaderboard v1 - HellaSwag | 56.6 | Normalized accuracy (%) (10-shot) | 12.7 |
| Open LLM Leaderboard v1 - WinoGrande | 58.48 | Accuracy (%) (5-shot) | 11.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 33.19 | Normalized accuracy (%) (25-shot) | 11.4 |
| Open LLM Leaderboard v1 - MMLU | 24.66 | Accuracy (%) (5-shot) | 4.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 36.28 | MC2 (%) (0-shot) | 3.5 |
Interactive version: theaggregate.ai/model?slug=llama-pile-350b · How It Works · Data refreshed daily, snapshot 2026-11-08.