72B-preview [bfloat16] [rev: 508ee8ddfd8B]: benchmark results

Provider: Other.

Aggregate Rating 1487 ± 38, rank #2560 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU77.14Accuracy (%) (5-shot)98.3
Open LLM Leaderboard v1 - GSM8K72.1Accuracy (%) (5-shot)97.2
Open LLM Leaderboard v1 - WinoGrande82.48Accuracy (%) (5-shot)84.3
Open LLM Leaderboard v1 - ARC Challenge65.19Normalized accuracy (%) (25-shot)69.3
Open LLM Leaderboard v1 - HellaSwag83.23Normalized accuracy (%) (10-shot)57
Open LLM Leaderboard v1 - TruthfulQA MC252.58MC2 (%) (0-shot)56.6

Interactive version: theaggregate.ai/model?slug=72b-preview-bfloat16-rev-508ee8ddfd8b · How It Works · Data refreshed daily, snapshot 2026-11-08.