token.app › Compare › GPT-5 Mini vs Gemma 4 31B
GPT-5 Mini vs Gemma 4 31B
GPT-5 Mini and Gemma 4 31B split the 2 shared benchmarks evenly. Gemma 4 31B is 2.8× cheaper per token on a blended 3:1 basis. GPT-5 Mini accepts the larger context window (400K).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5 Mini | Gemma 4 31B | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.250 | $0.200 |
| Output $/1M | $2.00 | $0.400 |
| Blended $/1M | $0.688 | $0.250 |
| Context window | 400K | 262K |
| Max output | 128K | 16K |
| Released | Aug 2025 | Apr 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 75.0% | 75.8% |
| OTIS Mock AIME | 86.7% | 73.3% |
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 GPT-5 Mini if…
- Higher OTIS Mock AIME (86.7% vs 73.3%)
- Larger context window (400K)
Choose Gemma 4 31B if…
- Costs less per token — $0.250 vs $0.688 blended
- Higher GPQA Diamond (75.8% vs 75.0%)
- Open weights — self-hostable
- Newer model (released Apr 2026)
FAQ
Which is better, GPT-5 Mini or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, GPT-5 Mini leads on 1 and Gemma 4 31B leads on 1. Benchmarks are one input — price and context window are on this page too.
Is GPT-5 Mini cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.250 versus $0.688 per million tokens blended at 3:1 input:output. Input alone: $0.250 vs $0.200. Output alone: $2.00 vs $0.400.
What context windows do GPT-5 Mini and Gemma 4 31B have?
GPT-5 Mini: 400,000 tokens. Gemma 4 31B: 262,144 tokens.
Who makes GPT-5 Mini and Gemma 4 31B?
GPT-5 Mini is made by OpenAI. Gemma 4 31B is made by Google.