ScarletPajama-3B-HF: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1142 ± 18, rank #10078 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Mathematics28.89Accuracy (%)67.8
MMLU-by-task - High School Physics31.79Accuracy (%)61.3
MMLU-by-task - Moral Scenarios27.26Accuracy (%)59.8
MMLU-by-task - High School Statistics39.35Accuracy (%)52.9
MMLU-by-task - College Chemistry34Accuracy (%)52.6
MMLU-by-task - College Mathematics31Accuracy (%)45.5
MMLU-by-task - Global Facts32Accuracy (%)44.3
MMLU-by-task - Elementary Mathematics27.51Accuracy (%)43.5
MMLU-by-task - College Physics23.53Accuracy (%)41.6
MMLU-by-task - Abstract Algebra28Accuracy (%)39.6
MMLU-by-task - College Medicine32.37Accuracy (%)37
MMLU-by-task - High School Microeconomics34.03Accuracy (%)36.9

Interactive version: theaggregate.ai/model?slug=scarletpajama-3b-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.