FINETUNE3_TEST4: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1321 ± 15, rank #8313 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Chemistry47Accuracy (%)92.1
MMLU-by-task - Formal Logic40.48Accuracy (%)87.2
MMLU-by-task - High School Statistics48.15Accuracy (%)87.1
MMLU-by-task - Philosophy66.56Accuracy (%)85.9
MMLU-by-task - Professional Accounting43.97Accuracy (%)83.3
MMLU-by-task - High School Macroeconomics52.82Accuracy (%)77.3
MMLU-by-task - High School US History75.98Accuracy (%)76.9
MMLU-by-task - Global Facts37Accuracy (%)76.3
MMLU-by-task - High School Mathematics30Accuracy (%)76.1
MMLU-by-task - Professional Law42.24Accuracy (%)76
MMLU-by-task - Professional Medicine53.68Accuracy (%)75.7
MMLU-by-task - Management72.82Accuracy (%)75.6

Interactive version: theaggregate.ai/model?slug=finetune3-test4 · How It Works · Data refreshed daily, snapshot 2026-11-08.