token.app › Compare › Gemma 4 31B vs GPT-5.6 Luna
Gemma 4 31B vs GPT-5.6 Luna
GPT-5.6 Luna leads on 3 of 3 shared benchmarks. Gemma 4 31B is 1.4× 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
| Gemma 4 31B | GPT-5.6 Luna | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.100 | $0.100 |
| Output $/1M | $0.340 | $0.600 |
| Blended $/1M | $0.160 | $0.225 |
| Context window | 262K | 1.1M |
| Max output | 262K | 128K |
| Released | Apr 2026 | Jul 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 75.8% | 91.6% |
| SimpleQA Verified | 9.6% | 41.7% |
| OTIS Mock AIME | 73.3% | 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 Gemma 4 31B if…
- Costs less per token — $0.160 vs $0.225 blended
- Open weights — self-hostable
Choose GPT-5.6 Luna if…
- Higher GPQA Diamond (91.6% vs 75.8%)
- Higher SimpleQA Verified (41.7% vs 9.6%)
- Higher OTIS Mock AIME (98.3% vs 73.3%)
- Larger context window (1.1M)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 4 31B or GPT-5.6 Luna?
Across the 3 benchmarks both models have independently-run scores for, Gemma 4 31B leads on 0 and GPT-5.6 Luna leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Gemma 4 31B cheaper than GPT-5.6 Luna?
Gemma 4 31B is cheaper: $0.160 versus $0.225 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.100. Output alone: $0.340 vs $0.600.
What context windows do Gemma 4 31B and GPT-5.6 Luna have?
Gemma 4 31B: 262,144 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Gemma 4 31B and GPT-5.6 Luna?
Gemma 4 31B is made by Google. GPT-5.6 Luna is made by OpenAI.