DiffMerge_Pygmalion_Main-onto-V8P4: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1146 ± 15, rank #10018 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Mathematics27.04Accuracy (%)50.6
MMLU-by-task - Professional Accounting30.14Accuracy (%)38.9
MMLU-by-task - Conceptual Physics34.04Accuracy (%)36.9
MMLU-by-task - Jurisprudence33.33Accuracy (%)34.3
MMLU-by-task - High School US History30.39Accuracy (%)34.2
MMLU-by-task - Astronomy31.58Accuracy (%)33.7
MMLU-by-task - Marketing33.33Accuracy (%)32.8
MMLU-by-task - HellaSwag50.51Accuracy (%)31.6
MMLU-by-task - Professional Law27.44Accuracy (%)31.4
MMLU-by-task - Professional Psychology28.1Accuracy (%)31.3
MMLU-by-task - Business Ethics32Accuracy (%)30.8
MMLU-by-task - Human Aging35.43Accuracy (%)30

Interactive version: theaggregate.ai/model?slug=diffmerge-pygmalion-main-onto-v8p4 · How It Works · Data refreshed daily, snapshot 2026-11-08.