llama-polyglot-13B: benchmark results
Provider: chargoddard. Access: Open.
Aggregate Rating 1361 ± 33, rank #7424 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 76.72 | Accuracy (%) (5-shot) | 50.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.81 | Normalized accuracy (%) (25-shot) | 45 |
| Open LLM Leaderboard v1 - HellaSwag | 81.27 | Normalized accuracy (%) (10-shot) | 44.3 |
| Open LLM Leaderboard v1 - GSM8K | 22.59 | Accuracy (%) (5-shot) | 42.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.71 | MC2 (%) (0-shot) | 42.3 |
| Open LLM Leaderboard v1 - MMLU | 55.04 | Accuracy (%) (5-shot) | 35.3 |
Interactive version: theaggregate.ai/model?slug=llama-polyglot-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.