mistral_rank32_dpo [bfloat16] [rev: eb9de643bae3]: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1400 ± 34, rank #6113 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC268.29MC2 (%) (0-shot)87.4
Open LLM Leaderboard v1 - HellaSwag85.01Normalized accuracy (%) (10-shot)71.1
Open LLM Leaderboard v1 - ARC Challenge63.14Normalized accuracy (%) (25-shot)61.5
Open LLM Leaderboard v1 - GSM8K38.89Accuracy (%) (5-shot)53.7
Open LLM Leaderboard v1 - WinoGrande76.64Accuracy (%) (5-shot)49.6
Open LLM Leaderboard v1 - MMLU60.57Accuracy (%) (5-shot)48.9

Interactive version: theaggregate.ai/model?slug=mistral-rank32-dpo-bfloat16-rev-eb9de643bae3 · How It Works · Data refreshed daily, snapshot 2026-11-08.