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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Epoch AI - Adversarial Nli | 90 | Score | 100 |
| Epoch AI - Common Sense Qa 2 | 94.1 | Score | 100 |
| Epoch AI - Superglue | 89.8 | Score | 100 |
| GameWorld Computer-Use | 64.1 | Progress (%) | 100 |
| GameWorld Generalist | 64.1 | Progress (%) | 100 |
| HellaSwag | 95.6 | Accuracy (%) | 100 |
| PIQA | 95 | Accuracy (%) | 100 |
| WebArena | 78.24 | Success Rate (%) | 100 |
| WinoGrande | 94 | Accuracy (%) | 100 |
| GSM8K | 95 | Accuracy (%) | 98.9 |
| SimpleBench | 83.7 | Score (AVG@5) | 98.9 |
| MMSI-Bench | 97.2 | Accuracy (%) | 98.7 |
Interactive version: theaggregate.ai/model?slug=median-human · How the rankings work · Data refreshed daily, snapshot 2026-07-22.