Median Human — benchmark results

Median-human baseline used as a reference point alongside model results. Provider: Human.

Unified ELO 1673 ± 70, rank #315 of 1776 rated models, from 57 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Epoch AI - Adversarial Nli90Score100
Epoch AI - Common Sense Qa 294.1Score100
Epoch AI - Superglue89.8Score100
GameWorld Computer-Use64.1Progress (%)100
GameWorld Generalist64.1Progress (%)100
HellaSwag95.6Accuracy (%)100
PIQA95Accuracy (%)100
WebArena78.24Success Rate (%)100
WinoGrande94Accuracy (%)100
GSM8K95Accuracy (%)98.9
SimpleBench83.7Score (AVG@5)98.9
MMSI-Bench97.2Accuracy (%)98.7

Interactive version: theaggregate.ai/model?slug=median-human · How the rankings work · Data refreshed daily, snapshot 2026-07-22.