AI Hub
← All models

Gemma 4 31B vs Qwen3.5 397B A17B

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

  • Qwen3.5 397B A17B has the higher intelligence index (89.3 vs 85.7)
  • Gemma 4 31B is cheaper ($0.12 vs $0.39 per 1M input)
  • Qwen3.5 397B A17B is faster
Gemma 4 31BQwen3.5 397B A17B
Intelligence index85.789.3
DeveloperGoogleAlibaba
TypeMultimodalMultimodal
AccessOpen weightsOpen weights
Context window262,144 tokens262,144 tokens
Input price$0.12 / 1M$0.39 / 1M
Output price$0.37 / 1M$2.34 / 1M
Speed36 tok/s53 tok/s
ReleasedApril 2, 2026February 16, 2026
Parameters
Input modalitiesImage, Text, VideoText, Image, Video
Output modalitiesTextText

Shared benchmarks

Gemma 4 31B
Qwen3.5 397B A17B
GPQA Diamond
85.7
89.3
Humanity’s Last Exam
22.7
27.3