AI Hub
← All models

Gemini 3 Flash vs Llama 3.2 90B Instruct

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

  • Gemini 3 Flash has the higher intelligence index (90.2 vs 54)
  • Llama 3.2 90B Instruct is cheaper ($0.35 vs $0.50 per 1M input)
  • Gemini 3 Flash is faster
  • Gemini 3 Flash has a larger context window (1M)
Gemini 3 FlashLlama 3.2 90B Instruct
Intelligence index90.254
DeveloperGoogleMeta
TypeMultimodalMultimodal
AccessAPI onlyOpen weights
Context window1,048,576 tokens128,000 tokens
Input price$0.50 / 1M$0.35 / 1M
Output price$3.00 / 1M$0.40 / 1M
Speed191 tok/s100 tok/s
ReleasedDecember 17, 2025September 25, 2024
Parameters90000000000
Input modalitiesText, Image, Audio, Video
Output modalitiesText

Shared benchmarks

Gemini 3 Flash
Llama 3.2 90B Instruct
GPQA Diamond
90.4
46.7
Humanity’s Last Exam
34.7
4.9
LiveCodeBench
90.8
21.4
MMLU-Pro
89
67.1