testlm2: benchmark results

Provider: Other.

Aggregate Rating 1315 ± 17, rank #8437 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Chemistry42Accuracy (%)80.4
MMLU-by-task - Security Studies62.86Accuracy (%)76.7
MMLU-by-task - Global Facts37Accuracy (%)76.3
MMLU-by-task - High School Physics33.77Accuracy (%)75
MMLU-by-task - Business Ethics55Accuracy (%)74.7
MMLU-by-task - Public Relations62.73Accuracy (%)74.3
MMLU-by-task - Econometrics31.58Accuracy (%)73.2
MMLU-by-task - Professional Accounting40.78Accuracy (%)72
MMLU-by-task - Anatomy48.89Accuracy (%)71.6
MMLU-by-task - High School European History67.27Accuracy (%)71.3
MMLU-by-task - Human Aging63.68Accuracy (%)71
MMLU-by-task - High School US History74.02Accuracy (%)70

Interactive version: theaggregate.ai/model?slug=testlm2 · How It Works · Data refreshed daily, snapshot 2026-11-08.