Bean-3B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1147 ± 16, rank #10015 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Mathematics37Accuracy (%)85.2
MMLU-by-task - High School Physics30.46Accuracy (%)50.8
MMLU-by-task - Elementary Mathematics26.98Accuracy (%)39.2
MMLU-by-task - Human Aging40.81Accuracy (%)37.5
MMLU-by-task - HellaSwag53.71Accuracy (%)37
MMLU-by-task - Global Facts31Accuracy (%)36.8
MMLU-by-task - High School Chemistry29.06Accuracy (%)36.1
MMLU-by-task - High School Mathematics25.93Accuracy (%)34.1
MMLU-by-task - Jurisprudence30.56Accuracy (%)31.6
MMLU-by-task - Miscellaneous30.52Accuracy (%)30.7
MMLU-by-task - Public Relations33.64Accuracy (%)30.2
MMLU-by-task - Virology31.93Accuracy (%)30

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