Llama 2 13B 12 153950: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1083 ± 18, rank #10862 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 49.03 | Accuracy (%) | 71.8 |
| MMLU-by-task - College Physics | 28.43 | Accuracy (%) | 67.4 |
| MMLU-by-task - Moral Scenarios | 28.38 | Accuracy (%) | 63.4 |
| MMLU-by-task - Econometrics | 29.82 | Accuracy (%) | 62.1 |
| MMLU-by-task - High School Mathematics | 27.04 | Accuracy (%) | 50.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 49.03 | MC2 (%) (0-shot) | 43.5 |
| MMLU-by-task - High School Physics | 27.15 | Accuracy (%) | 30.2 |
| MMLU-by-task - Elementary Mathematics | 26.19 | Accuracy (%) | 30 |
| MMLU-by-task - TruthfulQA MC1 | 24.6 | Accuracy (%) | 28.9 |
| MMLU-by-task - High School European History | 26.06 | Accuracy (%) | 22.2 |
| MMLU-by-task - College Computer Science | 28 | Accuracy (%) | 21.8 |
| MMLU-by-task - Business Ethics | 27 | Accuracy (%) | 21.4 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-12-153950 · How It Works · Data refreshed daily, snapshot 2026-11-08.