token.app › Compare › gpt-oss-120b vs Gemma 4 31B
gpt-oss-120b vs Gemma 4 31B
gpt-oss-120b leads on 1 of 2 shared benchmarks. Gemma 4 31B is 1.0× cheaper per token on a blended 3:1 basis. Gemma 4 31B accepts the larger context window (262K).
Head to head
Blended price uses a 3:1 input:output mix
| gpt-oss-120b | Gemma 4 31B | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.150 | $0.200 |
| Output $/1M | $0.600 | $0.400 |
| Blended $/1M | $0.262 | $0.250 |
| Context window | 131K | 262K |
| Max output | 66K | 16K |
| Released | Aug 2025 | Apr 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 75.8% | 75.8% |
| OTIS Mock AIME | 88.9% | 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-oss-120b if…
- Higher OTIS Mock AIME (88.9% vs 73.3%)
Choose Gemma 4 31B if…
- Costs less per token — $0.250 vs $0.262 blended
- Larger context window (262K)
- Newer model (released Apr 2026)
FAQ
Which is better, gpt-oss-120b or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, gpt-oss-120b leads on 1 and Gemma 4 31B leads on 0. Benchmarks are one input — price and context window are on this page too.
Is gpt-oss-120b cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.250 versus $0.262 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.200. Output alone: $0.600 vs $0.400.
What context windows do gpt-oss-120b and Gemma 4 31B have?
gpt-oss-120b: 131,072 tokens. Gemma 4 31B: 262,144 tokens.
Who makes gpt-oss-120b and Gemma 4 31B?
gpt-oss-120b is made by OpenAI. Gemma 4 31B is made by Google.