oasst-sft-1-pythia-12B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1137 ± 16, rank #10184 of 10916 rated models, from 75 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Physics27.45Accuracy (%)63
MMLU-by-task - Global Facts34Accuracy (%)58.4
MMLU-by-task - Abstract Algebra29Accuracy (%)45.4
MMLU-by-task - High School Physics28.48Accuracy (%)39.1
MMLU-by-task - Elementary Mathematics26.72Accuracy (%)36.2
MMLU-by-task - ARC Challenge41.3Accuracy (%)35.9
MMLU-by-task - HellaSwag52.38Accuracy (%)34.7
MMLU-by-task - Moral Scenarios24.47Accuracy (%)34.7
MMLU-by-task - High School US History30.88Accuracy (%)34.6
MMLU-by-task - High School Computer Science33Accuracy (%)33.8
MMLU-by-task - Astronomy30.92Accuracy (%)32.4
MMLU-by-task - Anatomy33.33Accuracy (%)32.1

Interactive version: theaggregate.ai/model?slug=oasst-sft-1-pythia-12b · How It Works · Data refreshed daily, snapshot 2026-11-08.