mistral-7B-tak-stack-dpo: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1408 ± 33, rank #5723 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande79.32Accuracy (%) (5-shot)68.6
Open LLM Leaderboard v1 - MMLU64.32Accuracy (%) (5-shot)68.2
Open LLM Leaderboard v1 - HellaSwag83.98Normalized accuracy (%) (10-shot)62.9
Open LLM Leaderboard v1 - GSM8K38.59Accuracy (%) (5-shot)53.4
Open LLM Leaderboard v1 - ARC Challenge61.18Normalized accuracy (%) (25-shot)51.6
Open LLM Leaderboard v1 - TruthfulQA MC243.8MC2 (%) (0-shot)24.8

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