Platypus2xOpenOrca-13B-IA3-ensemble: benchmark results

Provider: Other.

Aggregate Rating 1356 ± 17, rank #7552 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - Jurisprudence83.33Accuracy (%)98.1
MMLU-by-task - College Physics37.25Accuracy (%)92.9
MMLU-by-task - Computer Security74Accuracy (%)92
MMLU-by-task - High School US History83.82Accuracy (%)91.3
MMLU-by-task - Global Facts41Accuracy (%)90.8
MMLU-by-task - College Chemistry46Accuracy (%)90.3
MMLU-by-task - College Biology68.06Accuracy (%)90.1
MMLU-by-task - High School Statistics49.54Accuracy (%)90.1
MMLU-by-task - High School Geography77.78Accuracy (%)89.7
MMLU-by-task - College Medicine56.65Accuracy (%)89.6
MMLU-by-task - College Mathematics38Accuracy (%)89.5
MMLU-by-task - Human Sexuality69.47Accuracy (%)89.5

Interactive version: theaggregate.ai/model?slug=platypus2xopenorca-13b-ia3-ensemble · How It Works · Data refreshed daily, snapshot 2026-11-08.