model_51: benchmark results

Provider: pankajmathur. Access: Open.

Aggregate Rating 1435 ± 17, rank #4388 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Biology84.72Accuracy (%)99.5
MMLU-by-task - Miscellaneous87.23Accuracy (%)99
MMLU-by-task - High School US History92.16Accuracy (%)98.8
MMLU-by-task - College Chemistry51Accuracy (%)98.6
MMLU-by-task - Elementary Mathematics46.56Accuracy (%)98.6
MMLU-by-task - High School Biology82.58Accuracy (%)98.6
MMLU-by-task - Moral Disputes78.9Accuracy (%)98.5
MMLU-by-task - High School Physics47.68Accuracy (%)98.2
MMLU-by-task - Security Studies80Accuracy (%)98.1
MMLU-by-task - Computer Security78Accuracy (%)98
MMLU-by-task - Business Ethics75Accuracy (%)97.9
MMLU-by-task - Professional Psychology75.82Accuracy (%)97.9

Interactive version: theaggregate.ai/model?slug=model-51 · How It Works · Data refreshed daily, snapshot 2026-11-08.