AI Hub
← All models

Gemini 3.5 Flash vs Qwen3-235B-A22B-Instruct-2507

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

  • Gemini 3.5 Flash has the higher intelligence index (92.2 vs 72.2)
  • Qwen3-235B-A22B-Instruct-2507 is cheaper ($0.15 vs $1.50 per 1M input)
  • Gemini 3.5 Flash is faster
  • Gemini 3.5 Flash has a larger context window (1M)
Gemini 3.5 FlashQwen3-235B-A22B-Instruct-2507
Intelligence index92.272.2
DeveloperGoogleAlibaba
TypeMultimodalLLM
AccessAPI onlyOpen weights
Context window1,048,576 tokens131,072 tokens
Input price$1.50 / 1M$0.15 / 1M
Output price$9.00 / 1M$0.80 / 1M
Speed221 tok/s63 tok/s
ReleasedMay 19, 2026July 22, 2025
Parameters235000000000
Input modalitiesText, Image, Audio, Video
Output modalitiesText

Shared benchmarks

Gemini 3.5 Flash
Qwen3-235B-A22B-Instruct-2507
GPQA Diamond
92.2
77.5
Humanity’s Last Exam
41
10.6