Llama 2 13B AWQ: benchmark results
Provider: Meta. Released 2023-07-18. Access: Open.
Unified ELO 1308 ± 45, rank #2431 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Trustworthy - Fairness | 99.07 | Trust Score (%) | 83.3 |
| LLM Trustworthy - Ethics | 82.47 | Trust Score (%) | 75 |
| LLM Trustworthy - Adversarial | 50.35 | Trust Score (%) | 66.7 |
| AI-Secure LLM Trustworthy Leaderboard | 0.63 | Trustworthy average | 33.3 |
| LLM Trustworthy Leaderboard | 62.54 | Average Trust Score (%) | 33.3 |
| LLM Trustworthy - Out-of-Distribution | 55.65 | Trust Score (%) | 20.8 |
| LLM Trustworthy - Privacy | 75.53 | Trust Score (%) | 20.8 |
| LLM Trustworthy - Adversarial Demo | 49.48 | Trust Score (%) | 16.7 |
| LLM Trustworthy - Stereotype | 78 | Trust Score (%) | 16.7 |
| LLM Trustworthy - Toxicity | 23.4 | Trust Score (%) | 8.3 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-awq · How It Works · Data refreshed daily, snapshot 2026-09-19.