token.app โ€บ Compare โ€บ Gemini 3.1 Pro Preview vs GPT-5.6 Luna

Gemini 3.1 Pro Preview vs GPT-5.6 Luna

GPT-5.6 Luna leads on 3 of 5 shared benchmarks. GPT-5.6 Luna is 20ร— cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).

Head to head
Blended price uses a 3:1 input:output mix
Gemini 3.1 Pro PreviewGPT-5.6 Luna
ProviderGoogleOpenAI
Input $/1M$2.00$0.100
Output $/1M$12.00$0.600
Blended $/1M$4.50$0.225
Context window1.0M1.1M
Max output66K128K
ReleasedFeb 2026Jul 2026
LicenceProprietaryProprietary
GPQA Diamond 94.4% 91.6%
FrontierMath T1โ€“3 59.6% 82.1%
FrontierMath T4 26.8% 61.0%
SimpleQA Verified 77.3% 41.7%
OTIS Mock AIME 95.6% 98.3%
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 3.1 Pro Preview ifโ€ฆ
  • Higher GPQA Diamond (94.4% vs 91.6%)
  • Higher SimpleQA Verified (77.3% vs 41.7%)
Choose GPT-5.6 Luna ifโ€ฆ
  • Costs less per token โ€” $0.225 vs $4.50 blended
  • Higher FrontierMath T1โ€“3 (82.1% vs 59.6%)
  • Higher FrontierMath T4 (61.0% vs 26.8%)
  • Higher OTIS Mock AIME (98.3% vs 95.6%)
  • Larger context window (1.1M)
  • Newer model (released Jul 2026)
FAQ
Which is better, Gemini 3.1 Pro Preview or GPT-5.6 Luna?
Across the 5 benchmarks both models have independently-run scores for, Gemini 3.1 Pro Preview leads on 2 and GPT-5.6 Luna leads on 3. Benchmarks are one input โ€” price and context window are on this page too.
Is Gemini 3.1 Pro Preview cheaper than GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.225 versus $4.50 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.100. Output alone: $12.00 vs $0.600.
What context windows do Gemini 3.1 Pro Preview and GPT-5.6 Luna have?
Gemini 3.1 Pro Preview: 1,048,576 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Gemini 3.1 Pro Preview and GPT-5.6 Luna?
Gemini 3.1 Pro Preview is made by Google. GPT-5.6 Luna is made by OpenAI.
Related comparisons