test100 (Devio): benchmark results

Provider: Other.

Aggregate Rating 1133 ± 22, rank #10262 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Physics37.25Accuracy (%)92.9
MMLU-by-task - High School Statistics47.22Accuracy (%)83.3
MMLU-by-task - College Chemistry42Accuracy (%)80.4
MMLU-by-task - Formal Logic36.51Accuracy (%)76.5
MMLU-by-task - High School Physics33.11Accuracy (%)70.8
MMLU-by-task - Moral Scenarios27.04Accuracy (%)57.5
MMLU-by-task - Professional Medicine44.85Accuracy (%)45.7
MMLU-by-task - College Computer Science34Accuracy (%)39.6
MMLU-by-task - High School Macroeconomics36.41Accuracy (%)39.5
MMLU-by-task - High School Microeconomics34.87Accuracy (%)39.3
MMLU-by-task - Security Studies40Accuracy (%)39.1
MMLU-by-task - College Medicine32.95Accuracy (%)38.2

Interactive version: theaggregate.ai/model?slug=test100-devio · How It Works · Data refreshed daily, snapshot 2026-11-08.