Mistral-7B-Merge-14-v0.4: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1438 ± 34, rank #4274 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K70.81Accuracy (%) (5-shot)94.4
Open LLM Leaderboard v1 - MMLU65.1Accuracy (%) (5-shot)81.7
Open LLM Leaderboard v1 - HellaSwag86.15Normalized accuracy (%) (10-shot)79.1
Open LLM Leaderboard v1 - ARC Challenge66.81Normalized accuracy (%) (25-shot)74.8
Open LLM Leaderboard v1 - TruthfulQA MC258.25MC2 (%) (0-shot)72
Open LLM Leaderboard v1 - WinoGrande80.03Accuracy (%) (5-shot)72

Interactive version: theaggregate.ai/model?slug=mistral-7b-merge-14-v0-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.