AI Hub
← All models

Grok-4 Heavy vs Qwen3 VL 235B A22B Instruct

xAI vs Alibaba — benchmarks, pricing, and capabilities side by side.

  • Grok-4 Heavy has the higher intelligence index (89.3 vs 70.9)
Grok-4 HeavyQwen3 VL 235B A22B Instruct
Intelligence index89.370.9
DeveloperxAIAlibaba
TypeMultimodalMultimodal
AccessAPI onlyOpen weights
Context window262,144 tokens
Input price$0.20 / 1M
Output price$0.88 / 1M
Speed51 tok/s
ReleasedJuly 9, 2025September 23, 2025
Parameters
Input modalitiesText, Image
Output modalitiesText

Shared benchmarks

Grok-4 Heavy
Qwen3 VL 235B A22B Instruct
AIME 2025
100
70.7
GPQA Diamond
88.4
71.2
Humanity’s Last Exam
50.7
6.3
LiveCodeBench
79.4
59.4