AI Hub
← All models

Gemini 2.5 Flash-Lite vs Qwen3.6 Max

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

  • Qwen3.6 Max has the higher intelligence index (88.8 vs 72.3)
  • Gemini 2.5 Flash-Lite is cheaper ($0.10 vs $1.04 per 1M input)
Gemini 2.5 Flash-LiteQwen3.6 Max
Intelligence index72.388.8
DeveloperGoogleAlibaba
TypeLLMLLM
AccessAPI only
Context window262,144 tokens
Input price$0.10 / 1M$1.04 / 1M
Output price$0.40 / 1M$6.24 / 1M
Speed36 tok/s
ReleasedSeptember 8, 2025April 27, 2026
Parameters
Input modalitiesText
Output modalitiesText

Shared benchmarks

Gemini 2.5 Flash-Lite
Qwen3.6 Max
GPQA Diamond
70.9
88.8
Humanity’s Last Exam
6.6
28.9