AI Hub
← All models

GPT-5 Codex vs Qwen3 VL 32B Instruct

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

  • GPT-5 Codex has the higher intelligence index (87.1 vs 66.5)
  • Qwen3 VL 32B Instruct is cheaper ($0.10 vs $1.25 per 1M input)
  • GPT-5 Codex is faster
  • GPT-5 Codex has a larger context window (400K)
GPT-5 CodexQwen3 VL 32B Instruct
Intelligence index87.166.5
DeveloperOpenAIAlibaba
TypeMultimodalMultimodal
AccessAPI onlyOpen weights
Context window400,000 tokens262,144 tokens
Input price$1.25 / 1M$0.10 / 1M
Output price$10.00 / 1M$0.42 / 1M
Speed180 tok/s76 tok/s
ReleasedSeptember 23, 2025October 23, 2025
Parameters
Input modalitiesText, ImageText, Image
Output modalitiesTextText

Shared benchmarks

GPT-5 Codex
Qwen3 VL 32B Instruct
AIME 2025
98.7
68.3
GPQA Diamond
83.7
67.1
Humanity’s Last Exam
25.6
6.3
LiveCodeBench
84
51.4
MMLU-Pro
86.5
79.1