pygmalion-7B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1215 ± 15, rank #9517 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Mathematics33Accuracy (%)61.7
MMLU-by-task - HellaSwag57.61Accuracy (%)45.2
MMLU-by-task - ARC Challenge47.95Accuracy (%)44.5
MMLU-by-task - Conceptual Physics37.87Accuracy (%)44.3
MMLU-by-task - Global Facts32Accuracy (%)44.3
MMLU-by-task - Business Ethics44Accuracy (%)43.1
MMLU-by-task - Professional Medicine44.49Accuracy (%)42.8
MMLU-by-task - Public Relations49.09Accuracy (%)42.7
MMLU-by-task - Anatomy41.48Accuracy (%)42.1
MMLU-by-task - High School European History44.85Accuracy (%)40.5
MMLU-by-task - Nutrition39.87Accuracy (%)40.1
MMLU-by-task - International Law52.89Accuracy (%)40

Interactive version: theaggregate.ai/model?slug=pygmalion-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.