Codestral-22B-v0.1-hf: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1404 ± 34, rank #5867 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K62.02Accuracy (%) (5-shot)75
Open LLM Leaderboard v1 - TruthfulQA MC256.7MC2 (%) (0-shot)68.6
Open LLM Leaderboard v1 - ARC Challenge62.54Normalized accuracy (%) (25-shot)58.6
Open LLM Leaderboard v1 - MMLU62.21Accuracy (%) (5-shot)54.4
Open LLM Leaderboard v1 - HellaSwag81.76Normalized accuracy (%) (10-shot)46.9
Open LLM Leaderboard v1 - WinoGrande74.98Accuracy (%) (5-shot)39.7

Interactive version: theaggregate.ai/model?slug=codestral-22b-v0-1-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.