13B-Legerdemain-L2: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1347 ± 15, rank #7775 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - US Foreign Policy87Accuracy (%)93.2
MMLU-by-task - High School Chemistry49.26Accuracy (%)92.7
MMLU-by-task - College Chemistry47Accuracy (%)92.1
MMLU-by-task - Abstract Algebra36Accuracy (%)91.7
MMLU-by-task - Jurisprudence77.78Accuracy (%)91.3
MMLU-by-task - Clinical Knowledge63.77Accuracy (%)89.7
MMLU-by-task - Anatomy52.59Accuracy (%)87.3
MMLU-by-task - High School Mathematics31.48Accuracy (%)85
MMLU-by-task - Sociology76.62Accuracy (%)84.3
MMLU-by-task - Nutrition62.75Accuracy (%)84.1
MMLU-by-task - College Biology62.5Accuracy (%)84
MMLU-by-task - HellaSwag63.54Accuracy (%)83.7

Interactive version: theaggregate.ai/model?slug=13b-legerdemain-l2 · How It Works · Data refreshed daily, snapshot 2026-11-08.