Median Human: benchmark results

Median performance for the measured general-human population, used as a reference point alongside model results. Provider: Human.

Unified ELO 1709 ± 17, rank #46 of 1392 rated models, from 35 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BabyVision94.1Score (%)100
Epoch AI - Common Sense Qa 294.1Score100
Epoch AI - Superglue89.8Score100
GSM8K95Accuracy (%)100
GameWorld Computer-Use64.1Progress (%)100
GameWorld Generalist64.1Progress (%)100
HellaSwag95.6Accuracy (%)100
OpenBookQA92Accuracy (%)100
PIQA95Accuracy (%)100
WebArena78.24Success Rate (%)100
WinoGrande94Accuracy (%)100
SimpleBench83.7Score (AVG@5)99

Interactive version: theaggregate.ai/model?slug=median-human · How It Works · Data refreshed daily, snapshot 2026-09-05.