Mistral-12.25B-v0.2: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1392 ± 33, rank #6442 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU63.22Accuracy (%) (5-shot)59.1
Open LLM Leaderboard v1 - WinoGrande77.66Accuracy (%) (5-shot)57.6
Open LLM Leaderboard v1 - GSM8K32.07Accuracy (%) (5-shot)48.5
Open LLM Leaderboard v1 - HellaSwag81.77Normalized accuracy (%) (10-shot)46.9
Open LLM Leaderboard v1 - ARC Challenge58.87Normalized accuracy (%) (25-shot)41.2
Open LLM Leaderboard v1 - TruthfulQA MC240.44MC2 (%) (0-shot)14.2

Interactive version: theaggregate.ai/model?slug=mistral-12-25b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.