PPO_Pygway-V8p4_Dev-6B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1168 ± 15, rank #9785 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Mathematics31Accuracy (%)45.5
MMLU-by-task - Abstract Algebra29Accuracy (%)45.4
MMLU-by-task - Moral Scenarios24.92Accuracy (%)43
MMLU-by-task - Security Studies42.04Accuracy (%)42.6
MMLU-by-task - College Physics23.53Accuracy (%)41.6
MMLU-by-task - Astronomy36.84Accuracy (%)39.7
MMLU-by-task - Econometrics27.19Accuracy (%)39.6
MMLU-by-task - Professional Law29.66Accuracy (%)37.3
MMLU-by-task - Global Facts31Accuracy (%)36.8
MMLU-by-task - International Law44.63Accuracy (%)36.2
MMLU-by-task - High School Macroeconomics35.38Accuracy (%)35.5
MMLU-by-task - Sociology37.31Accuracy (%)34.9

Interactive version: theaggregate.ai/model?slug=ppo-pygway-v8p4-dev-6b · How It Works · Data refreshed daily, snapshot 2026-11-08.