In short
How they differ.
Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.
- Gemma 4 31B reads more at once: a context window of 256K tokens against 128K.
- Both can be downloaded and run on your own machine.
- No independent board we follow ranks both models yet.
Side by side
The specs.
| Gemma 4 31B | gpt-oss-120b | |
|---|---|---|
| Made by | Google · US | OpenAI · US |
| Released | Apr 2, 2026 | Aug 5, 2025 |
| Price per 1M tokens | Free to download; hosts set prices | Free to download; hosts set prices |
| Context window | 256K | 128K |
| Takes in | text, image, video | text |
| Download and run it yourself | Yes (Apache 2.0) | Yes (Apache 2.0) |
| Size | 30.7B (dense) parameters | 117B parameters, 5.1B active |
| Maker says | “Today, we are introducing Gemma 4 — our most intelligent open models to date.” | “production, general purpose, high reasoning use cases” |
| Sources | Prices, Oct 20, 2026 · Description | Prices, Oct 20, 2026 · Description |
Independent tests
Where they place.
Position on each board we follow (1 is best). Epoch AI's and Vectara's scores are shown; the other boards are linked for their own figures.
| Board | Gemma 4 31B | gpt-oss-120b |
|---|---|---|
| Vectara hallucination testVectara, Oct 16, 2026 | Not listed | #9214.2% |
More comparisons