AI Hub
← All models

GPT-5.2-Codex vs Qwen3 VL 8B Instruct

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

  • GPT-5.2-Codex has the higher intelligence index (89.9 vs 43)
  • Qwen3 VL 8B Instruct is cheaper ($0.08 vs $1.75 per 1M input)
  • Qwen3 VL 8B Instruct is faster
  • GPT-5.2-Codex has a larger context window (400K)
GPT-5.2-CodexQwen3 VL 8B Instruct
Intelligence index89.943
DeveloperOpenAIAlibaba
TypeMultimodalMultimodal
AccessAPI onlyOpen weights
Context window400,000 tokens256,000 tokens
Input price$1.75 / 1M$0.08 / 1M
Output price$14.00 / 1M$0.50 / 1M
Speed106 tok/s145 tok/s
ReleasedJanuary 14, 2026October 14, 2025
Parameters
Input modalitiesText, ImageImage, Text
Output modalitiesTextText

Shared benchmarks

GPT-5.2-Codex
Qwen3 VL 8B Instruct
GPQA Diamond
89.9
42.7
Humanity’s Last Exam
33.5
2.9