pythia-6.9B-deduped: benchmark results

Provider: EleutherAI. Access: Open.

Aggregate Rating 1142 ± 15, rank #10075 of 10916 rated models, from 73 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Statistics44.91Accuracy (%)73.4
MMLU-by-task - High School Physics31.13Accuracy (%)56.1
MMLU-by-task - Machine Learning33.04Accuracy (%)53.4
MMLU-by-task - High School Mathematics26.67Accuracy (%)45.9
MMLU-by-task - College Mathematics31Accuracy (%)45.5
MMLU-by-task - High School Chemistry30.54Accuracy (%)42.1
MMLU-by-task - College Computer Science35Accuracy (%)42
MMLU-by-task - Virology34.94Accuracy (%)37.7
MMLU-by-task - Logical Fallacies31.29Accuracy (%)34.1
MMLU-by-task - Abstract Algebra27Accuracy (%)34
MMLU-by-task - Human Aging37.67Accuracy (%)33.2
MMLU-by-task - Electrical Engineering30.34Accuracy (%)32.9

Interactive version: theaggregate.ai/model?slug=pythia-6-9b-deduped · How It Works · Data refreshed daily, snapshot 2026-11-08.