Llama 2 13B Chat AWQ: benchmark results
Provider: Meta. Released 2023-07-18. Access: Open.
Unified ELO 1431 ± 46, rank #1656 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Trustworthy - Stereotype | 100 | Trust Score (%) | 93.8 |
| LLM Trustworthy - Toxicity | 80.96 | Trust Score (%) | 91.7 |
| LLM Trustworthy - Privacy | 96.31 | Trust Score (%) | 87.5 |
| AI-Secure LLM Trustworthy Leaderboard | 0.71 | Trustworthy average | 66.7 |
| LLM Trustworthy Leaderboard | 71.32 | Average Trust Score (%) | 66.7 |
| LLM Trustworthy - Adversarial Demo | 66.29 | Trust Score (%) | 58.3 |
| LLM Trustworthy - Ethics | 62.81 | Trust Score (%) | 54.2 |
| LLM Trustworthy - Fairness | 78.19 | Trust Score (%) | 25 |
| LLM Trustworthy - Out-of-Distribution | 58.38 | Trust Score (%) | 25 |
| LLM Trustworthy - Adversarial | 41.99 | Trust Score (%) | 12.5 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-chat-awq · How It Works · Data refreshed daily, snapshot 2026-09-19.