Mistral-7B-FFT-Test3 [bfloat16] [rev: ff6ab8204162]: benchmark results

Provider: Mistral.

Aggregate Rating 1390 ± 33, rank #6514 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - WinoGrande77.82Accuracy (%) (5-shot)58.7
Open LLM Leaderboard v1 - MMLU62.2Accuracy (%) (5-shot)54.4
Open LLM Leaderboard v1 - HellaSwag82.36Normalized accuracy (%) (10-shot)50.7
Open LLM Leaderboard v1 - ARC Challenge60.24Normalized accuracy (%) (25-shot)46.8
Open LLM Leaderboard v1 - GSM8K26.76Accuracy (%) (5-shot)44.8
Open LLM Leaderboard v1 - TruthfulQA MC244.36MC2 (%) (0-shot)26.9

Interactive version: theaggregate.ai/model?slug=mistral-7b-fft-test3-bfloat16-rev-ff6ab8204162 · How It Works · Data refreshed daily, snapshot 2026-11-08.