Huginn-13B-V4: benchmark results

Provider: Other.

Aggregate Rating 1323 ± 15, rank #8286 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - Management75.73Accuracy (%)84.7
MMLU-by-task - College Chemistry43Accuracy (%)83.5
MMLU-by-task - ARC Challenge57.51Accuracy (%)81.2
MMLU-by-task - HellaSwag62.86Accuracy (%)79.6
MMLU-by-task - TruthfulQA MC250.62Accuracy (%)79
MMLU-by-task - College Physics31.37Accuracy (%)77.6
MMLU-by-task - TruthfulQA MC134.39Accuracy (%)77.3
MMLU-by-task - High School Mathematics30Accuracy (%)76.1
MMLU-by-task - Anatomy49.63Accuracy (%)75.9
MMLU-by-task - Security Studies62.45Accuracy (%)74.9
MMLU-by-task - Human Aging64.57Accuracy (%)74.3
MMLU-by-task - High School Biology64.19Accuracy (%)73.2

Interactive version: theaggregate.ai/model?slug=huginn-13b-v4 · How It Works · Data refreshed daily, snapshot 2026-11-08.