pile-7B: benchmark results

Provider: Other.

Aggregate Rating 1135 ± 19, rank #10225 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Mathematics33.33Accuracy (%)93.3
MMLU-by-task - High School Statistics46.3Accuracy (%)78.9
MMLU-by-task - College Physics28.43Accuracy (%)67.4
MMLU-by-task - College Mathematics33Accuracy (%)61.7
MMLU-by-task - College Computer Science35Accuracy (%)42
MMLU-by-task - TruthfulQA MC242.41Accuracy (%)39.2
MMLU-by-task - Professional Medicine42.28Accuracy (%)36.6
MMLU-by-task - Security Studies38.78Accuracy (%)36.6
MMLU-by-task - High School Computer Science33Accuracy (%)33.8
MMLU-by-task - High School Geography35.86Accuracy (%)33.8
MMLU-by-task - High School Government And Politics36.79Accuracy (%)33.5
MMLU-by-task - Machine Learning28.57Accuracy (%)30.8

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