Athena-v1: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1343 ± 15, rank #7885 of 10916 rated models, from 68 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - College Computer Science51Accuracy (%)89.8
MMLU-by-task - Global Facts40Accuracy (%)88.7
MMLU-by-task - Virology49.4Accuracy (%)87.4
MMLU-by-task - High School Chemistry45.32Accuracy (%)85.7
MMLU-by-task - Electrical Engineering53.1Accuracy (%)85.4
MMLU-by-task - Human Aging66.82Accuracy (%)84
MMLU-by-task - Business Ethics58Accuracy (%)83.8
MMLU-by-task - Prehistory65.74Accuracy (%)83.3
MMLU-by-task - US Foreign Policy83Accuracy (%)83.1
MMLU-by-task - Computer Security70Accuracy (%)82.7
MMLU-by-task - College Medicine53.18Accuracy (%)81.9
MMLU-by-task - Jurisprudence72.22Accuracy (%)81.6

Interactive version: theaggregate.ai/model?slug=athena-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.