loyal-piano-m7-cdpo [float16] [rev: 5f5a78bedc2d]: benchmark results

Provider: chargoddard. Access: Open.

Aggregate Rating 1431 ± 34, rank #4626 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC261.54MC2 (%) (0-shot)77.9
Open LLM Leaderboard v1 - ARC Challenge67.06Normalized accuracy (%) (25-shot)75.6
Open LLM Leaderboard v1 - HellaSwag85.42Normalized accuracy (%) (10-shot)74.3
Open LLM Leaderboard v1 - MMLU64.54Accuracy (%) (5-shot)72.3
Open LLM Leaderboard v1 - GSM8K56.33Accuracy (%) (5-shot)68
Open LLM Leaderboard v1 - WinoGrande79.08Accuracy (%) (5-shot)67.2

Interactive version: theaggregate.ai/model?slug=loyal-piano-m7-cdpo-float16-rev-5f5a78bedc2d · How It Works · Data refreshed daily, snapshot 2026-11-08.