mistral-orpo-beta: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1400 ± 26, rank #6094 of 10916 rated models, from 8 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande79.24Accuracy (%) (5-shot)68.1
Open LLM Leaderboard v1 - HellaSwag84.03Normalized accuracy (%) (10-shot)63.2
Open LLM Leaderboard v1 - MMLU63.26Accuracy (%) (5-shot)59.4
BiGGen-Bench3.47Average Score (1-5)58.8
Open LLM Leaderboard v1 - GSM8K39.8Accuracy (%) (5-shot)54.9
Open LLM Leaderboard v1 - ARC Challenge61.18Normalized accuracy (%) (25-shot)51.6
Open LLM Leaderboard v1 - TruthfulQA MC247.69MC2 (%) (0-shot)38.4
AlpacaEval 2.014.72LC Win Rate (%)37.8

Interactive version: theaggregate.ai/model?slug=mistral-orpo-beta · How It Works · Data refreshed daily, snapshot 2026-11-08.