Mistral_7B_SFT_DPO_v0: benchmark results

Provider: Mistral.

Aggregate Rating 1438 ± 35, rank #4285 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC269.72MC2 (%) (0-shot)89.3
Open LLM Leaderboard v1 - WinoGrande81.77Accuracy (%) (5-shot)80.8
Open LLM Leaderboard v1 - GSM8K65.81Accuracy (%) (5-shot)80.6
Open LLM Leaderboard v1 - ARC Challenge66.3Normalized accuracy (%) (25-shot)73
Open LLM Leaderboard v1 - MMLU64.53Accuracy (%) (5-shot)72.1
Open LLM Leaderboard v1 - HellaSwag84.9Normalized accuracy (%) (10-shot)70

Interactive version: theaggregate.ai/model?slug=mistral-7b-sft-dpo-v0 · How It Works · Data refreshed daily, snapshot 2026-11-08.