Grok 4 (verifiable): benchmark results

Provider: xAI. Access: API.

Aggregate Rating 1729 ± 27, rank #238 of 10916 rated models, from 1 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Medmarks0.63Win Rate96.2

Interactive version: theaggregate.ai/model?slug=grok-4-verifiable · How It Works · Data refreshed daily, snapshot 2026-11-08.