Llama 2 13B Math1.2 [float16] [rev: B05b4c22893e]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1341 ± 34, rank #7954 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 80.71 | Normalized accuracy (%) (10-shot) | 42 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.25 | MC2 (%) (0-shot) | 40.4 |
| Open LLM Leaderboard v1 - WinoGrande | 74.74 | Accuracy (%) (5-shot) | 38.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.91 | Normalized accuracy (%) (25-shot) | 36.3 |
| Open LLM Leaderboard v1 - GSM8K | 11.3 | Accuracy (%) (5-shot) | 32.7 |
| Open LLM Leaderboard v1 - MMLU | 53.21 | Accuracy (%) (5-shot) | 32.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-math1-2-float16-rev-b05b4c22893e · How It Works · Data refreshed daily, snapshot 2026-11-08.