test-22B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1139 ± 18, rank #10136 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Physics36.42Accuracy (%)86.3
MMLU-by-task - College Physics29.41Accuracy (%)71.1
MMLU-by-task - College Chemistry37Accuracy (%)62.4
MMLU-by-task - Global Facts33Accuracy (%)51.6
MMLU-by-task - High School Statistics38.89Accuracy (%)51.5
MMLU-by-task - Professional Medicine44.85Accuracy (%)45.7
MMLU-by-task - High School Microeconomics35.29Accuracy (%)40.4
MMLU-by-task - High School Mathematics26.3Accuracy (%)40
MMLU-by-task - Elementary Mathematics26.98Accuracy (%)39.2
MMLU-by-task - Security Studies40Accuracy (%)39.1
MMLU-by-task - High School Chemistry29.56Accuracy (%)38.5
MMLU-by-task - High School Macroeconomics35.64Accuracy (%)36.4

Interactive version: theaggregate.ai/model?slug=test-22b · How It Works · Data refreshed daily, snapshot 2026-11-08.