Mistral-7B-OpenOrca — benchmark results

Provider: Mistral. Released 2023-09-29. Access: Open.

Unified ELO 1261 ± 27, rank #1596 of 1776 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Trustworthy - Out-of-Distribution73.4Trust Score (%)76
LLM Trustworthy - Adversarial47.23Trust Score (%)60
Open LLM Leaderboard - IFEval49.78Score58.5
Open Korean LLM Leaderboard193.84Average Score (%)58.4
LLM Trustworthy - Adversarial Demo62.15Trust Score (%)52
Open LLM Leaderboard - BBH25.84Score39.9
LLM Trustworthy - Privacy77.36Trust Score (%)36
Open LLM Leaderboard - MuSR5.89Score28.3
Open LLM Leaderboard - MMLU-Pro18.37Score28
Open LLM Leaderboard - GPQA2.91Score26.7
LLM Trustworthy - Stereotype79.33Trust Score (%)24
LLM Trustworthy - Toxicity30.12Trust Score (%)24

Interactive version: theaggregate.ai/model?slug=mistral-7b-openorca · How the rankings work · Data refreshed daily, snapshot 2026-07-22.