Mistral-4B-FT-2: benchmark results

Provider: Mistral. Access: Open.

Aggregate Rating 1128 ± 37, rank #10375 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC246.33MC2 (%) (0-shot)34.1
Open LLM Leaderboard v1 - GSM8K2.88Accuracy (%) (5-shot)20.9
Open LLM Leaderboard v1 - WinoGrande56.59Accuracy (%) (5-shot)9.9
Open LLM Leaderboard v1 - MMLU25.46Accuracy (%) (5-shot)8.5
Open LLM Leaderboard v1 - HellaSwag39.63Normalized accuracy (%) (10-shot)8
Open LLM Leaderboard v1 - ARC Challenge25.94Normalized accuracy (%) (25-shot)5.3

Interactive version: theaggregate.ai/model?slug=mistral-4b-ft-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.