Llama 2 13B Chat Gptq: benchmark results
Provider: Meta. Released 2023-07-18. Access: Open.
Unified ELO 1428 ± 46, rank #1685 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Trustworthy - Privacy | 98.88 | Trust Score (%) | 100 |
| LLM Trustworthy - Stereotype | 100 | Trust Score (%) | 93.8 |
| LLM Trustworthy - Toxicity | 80.87 | Trust Score (%) | 87.5 |
| AI-Secure LLM Trustworthy Leaderboard | 0.72 | Trustworthy average | 70.8 |
| LLM Trustworthy Leaderboard | 71.99 | Average Trust Score (%) | 70.8 |
| LLM Trustworthy - Adversarial Demo | 67.2 | Trust Score (%) | 62.5 |
| LLM Trustworthy - Ethics | 53.93 | Trust Score (%) | 45.8 |
| LLM Trustworthy - Fairness | 89.67 | Trust Score (%) | 45.8 |
| LLM Trustworthy - Out-of-Distribution | 59.1 | Trust Score (%) | 31.2 |
| LLM Trustworthy - Adversarial | 37.12 | Trust Score (%) | 4.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-chat-gptq · How It Works · Data refreshed daily, snapshot 2026-09-19.