vicuna-13B-v1.3-awq: benchmark results

Provider: LMSYS. Released 2023-10-04. Access: Open.

Unified ELO 1333 ± 45, rank #2327 of 2656 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Trustworthy - Adversarial Demo62.49Trust Score (%)54.2
LLM Trustworthy - Privacy79.55Trust Score (%)54.2
LLM Trustworthy - Ethics57.77Trust Score (%)50
LLM Trustworthy - Out-of-Distribution61.61Trust Score (%)37.5
LLM Trustworthy - Stereotype82.33Trust Score (%)33.3
LLM Trustworthy - Toxicity30.61Trust Score (%)29.2
AI-Secure LLM Trustworthy Leaderboard0.6Trustworthy average16.7
LLM Trustworthy - Adversarial42.19Trust Score (%)16.7
LLM Trustworthy - Fairness76.42Trust Score (%)16.7
LLM Trustworthy Leaderboard60.14Average Trust Score (%)16.7

Interactive version: theaggregate.ai/model?slug=vicuna-13b-v1-3-awq · How It Works · Data refreshed daily, snapshot 2026-09-19.