metharme-1.3B-finetuned: benchmark results

Provider: Other.

Aggregate Rating 1129 ± 19, rank #10344 of 10916 rated models, from 62 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - High School Statistics47.22Accuracy (%)83.3
MMLU-by-task - High School Mathematics28.52Accuracy (%)64.7
MMLU-by-task - College Chemistry34Accuracy (%)52.6
MMLU-by-task - TruthfulQA MC244.8Accuracy (%)50.4
MMLU-by-task - College Medicine34.68Accuracy (%)40.8
MMLU-by-task - High School Chemistry29.06Accuracy (%)36.1
MMLU-by-task - College Physics22.55Accuracy (%)34.3
MMLU-by-task - High School Microeconomics31.09Accuracy (%)32.7
MMLU-by-task - Professional Medicine38.6Accuracy (%)31.8
MMLU-by-task - High School Biology30.65Accuracy (%)30.7
MMLU-by-task - Nutrition28.43Accuracy (%)27.5
MMLU-by-task - Anatomy30.37Accuracy (%)26.9

Interactive version: theaggregate.ai/model?slug=metharme-1-3b-finetuned · How It Works · Data refreshed daily, snapshot 2026-11-08.