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

BenchmarkScoreMetricPercentile
LLM Trustworthy - Fairness99.07Trust Score (%)83.3
LLM Trustworthy - Ethics82.47Trust Score (%)75
LLM Trustworthy - Adversarial50.35Trust Score (%)66.7
AI-Secure LLM Trustworthy Leaderboard0.63Trustworthy average33.3
LLM Trustworthy Leaderboard62.54Average Trust Score (%)33.3
LLM Trustworthy - Out-of-Distribution55.65Trust Score (%)20.8
LLM Trustworthy - Privacy75.53Trust Score (%)20.8
LLM Trustworthy - Adversarial Demo49.48Trust Score (%)16.7
LLM Trustworthy - Stereotype78Trust Score (%)16.7
LLM Trustworthy - Toxicity23.4Trust Score (%)8.3

Interactive version: theaggregate.ai/model?slug=llama-2-13b-awq · How It Works · Data refreshed daily, snapshot 2026-09-19.