Mistral-v0.1-PeanutButter-v0.0.5-DPO-7B-QLoRA [Adapter]: benchmark results

Provider: Mistral.

Aggregate Rating 1399 ± 34, rank #6147 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - HellaSwag84.52Normalized accuracy (%) (10-shot)66.6
Open LLM Leaderboard v1 - WinoGrande78.61Accuracy (%) (5-shot)64.3
Open LLM Leaderboard v1 - MMLU63.63Accuracy (%) (5-shot)62
Open LLM Leaderboard v1 - ARC Challenge61.26Normalized accuracy (%) (25-shot)52
Open LLM Leaderboard v1 - GSM8K18.12Accuracy (%) (5-shot)39.5
Open LLM Leaderboard v1 - TruthfulQA MC245.75MC2 (%) (0-shot)32

Interactive version: theaggregate.ai/model?slug=mistral-v0-1-peanutbutter-v0-0-5-dpo-7b-qlora-adapter · How It Works · Data refreshed daily, snapshot 2026-11-08.