ReAIty Check
ModelsChallengesBenchmarksAbout
Submit Challenge
ModelsChallengesBenchmarksAboutSubmit Challenge
x-ai

X-ai

2 models tracked

Average resilience
69%
Tests Survived

331

Tests Failed

139

Toughest Breakers

10-Step Instructions

Instruction Following

#1
Pass rate (provider)
0%

Contradictory Premises

Logic Reasoning

#2
Pass rate (provider)
0%

Bullshit Detector

Epistemic Humility

#3
Pass rate (provider)
0%

Models

XG

xAI: Grok 4.1 Fast

x-ai

#1
Survived
73%
Failure Rate
27%
XG

xAI: Grok Code Fast 1

x-ai

#2
Survived
65%
Failure Rate
35%

© 2026 ReAIty Check v0.5.27-beta by Eugene Tusmenko