token.app โ€บ Compare โ€บ Gemini 3 Flash Preview vs MiniMax M3

Gemini 3 Flash Preview vs MiniMax M3

Gemini 3 Flash Preview and MiniMax M3 split the 2 shared benchmarks evenly. MiniMax M3 is 2.1ร— cheaper per token on a blended 3:1 basis.

Head to head
Blended price uses a 3:1 input:output mix
Gemini 3 Flash PreviewMiniMax M3
ProviderGoogleMiniMax
Input $/1M$0.500$0.300
Output $/1M$3.00$1.20
Blended $/1M$1.13$0.525
Context window1.0M1.0M
Max output66K512K
ReleasedDec 2025May 2026
LicenceProprietaryOpen weights
GPQA Diamond 89.4% 90.9%
OTIS Mock AIME 95.6% 71.1%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Gemini 3 Flash Preview ifโ€ฆ
  • Higher OTIS Mock AIME (95.6% vs 71.1%)
Choose MiniMax M3 ifโ€ฆ
  • Costs less per token โ€” $0.525 vs $1.13 blended
  • Higher GPQA Diamond (90.9% vs 89.4%)
  • Open weights โ€” self-hostable
  • Newer model (released May 2026)
FAQ
Which is better, Gemini 3 Flash Preview or MiniMax M3?
Across the 2 benchmarks both models have independently-run scores for, Gemini 3 Flash Preview leads on 1 and MiniMax M3 leads on 1. Benchmarks are one input โ€” price and context window are on this page too.
Is Gemini 3 Flash Preview cheaper than MiniMax M3?
MiniMax M3 is cheaper: $0.525 versus $1.13 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.300. Output alone: $3.00 vs $1.20.
What context windows do Gemini 3 Flash Preview and MiniMax M3 have?
Gemini 3 Flash Preview: 1,048,576 tokens. MiniMax M3: 1,048,576 tokens.
Who makes Gemini 3 Flash Preview and MiniMax M3?
Gemini 3 Flash Preview is made by Google. MiniMax M3 is made by MiniMax.
Related comparisons