Grok 4.6 (Low): benchmark results

Provider: xAI. Released 2026-08-12. Access: API.

Unified ELO 1687 ± 1, rank #137 of 1761 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Omniscience25.9Score94.5
AA-LCR78.67Accuracy (self-reported)93
AA Long Context Reasoning80.67Accuracy (%)91.8
Artificial Analysis Intelligence Index41.8Intelligence Index91.7
AA Omniscience - Software Engineering (SWE)67.3Accuracy (%)89.1
AA Omniscience - Science, Engineering & Mathematics46.2Accuracy (%)89
AA Omniscience - Law37.5Accuracy (%)86.8
AA-Omniscience Accuracy43.28Accuracy (%)86.5
AA Omniscience - Health38.9Accuracy (%)86
AA GPQA Diamond87.88Accuracy (%)84.4
AA GDPval1467.28ELO83.5
AA Omniscience - Humanities & Social Sciences38.3Accuracy (%)83

Interactive version: theaggregate.ai/model?slug=grok-4-6-low · How It Works · Data refreshed daily, snapshot 2026-09-05.