token.app › Compare › Gemma 3 27B vs GPT-5 Nano
Gemma 3 27B vs GPT-5 Nano
GPT-5 Nano leads on 2 of 2 shared benchmarks. GPT-5 Nano is 1.3× cheaper per token on a blended 3:1 basis. GPT-5 Nano accepts the larger context window (400K).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 3 27B | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.080 | $0.050 |
| Output $/1M | $0.450 | $0.400 |
| Blended $/1M | $0.172 | $0.138 |
| Context window | 262K | 400K |
| Max output | 131K | 128K |
| Released | Mar 2025 | Aug 2025 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 43.9% | 69.4% |
| OTIS Mock AIME | 22.2% | 81.1% |
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 Gemma 3 27B if…
- Open weights — self-hostable
Choose GPT-5 Nano if…
- Costs less per token — $0.138 vs $0.172 blended
- Higher GPQA Diamond (69.4% vs 43.9%)
- Higher OTIS Mock AIME (81.1% vs 22.2%)
- Larger context window (400K)
- Newer model (released Aug 2025)
FAQ
Which is better, Gemma 3 27B or GPT-5 Nano?
Across the 2 benchmarks both models have independently-run scores for, Gemma 3 27B leads on 0 and GPT-5 Nano leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Gemma 3 27B cheaper than GPT-5 Nano?
GPT-5 Nano is cheaper: $0.138 versus $0.172 per million tokens blended at 3:1 input:output. Input alone: $0.080 vs $0.050. Output alone: $0.450 vs $0.400.
What context windows do Gemma 3 27B and GPT-5 Nano have?
Gemma 3 27B: 262,144 tokens. GPT-5 Nano: 400,000 tokens.
Who makes Gemma 3 27B and GPT-5 Nano?
Gemma 3 27B is made by Google. GPT-5 Nano is made by OpenAI.