CrimsonPajama: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1142 ± 15, rank #10070 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Mathematics26.67Accuracy (%)45.9
MMLU-by-task - Abstract Algebra29Accuracy (%)45.4
MMLU-by-task - Electrical Engineering32.41Accuracy (%)36.5
MMLU-by-task - Elementary Mathematics26.72Accuracy (%)36.2
MMLU-by-task - Machine Learning29.46Accuracy (%)35.2
MMLU-by-task - Econometrics26.32Accuracy (%)32.9
MMLU-by-task - College Chemistry27Accuracy (%)32.3
MMLU-by-task - Anatomy33.33Accuracy (%)32.1
MMLU-by-task - International Law38.02Accuracy (%)32
MMLU-by-task - Logical Fallacies30.06Accuracy (%)31.4
MMLU-by-task - High School Physics27.15Accuracy (%)30.2
MMLU-by-task - Professional Law27.18Accuracy (%)29.9

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