In short
How they differ.
Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.
- MiniMax-M3 reads more at once: a context window of 1M 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.
| gpt-oss-120b | MiniMax-M3 | |
|---|---|---|
| Made by | OpenAI · US | MiniMax · China |
| Released | Aug 5, 2025 | Not stated |
| Price per 1M tokens | Free to download; hosts set prices | $0.30 in / $1.20 out |
| Context window | 128K | 1M |
| Takes in | text | text |
| Download and run it yourself | Yes (Apache 2.0) | Yes (minimax-community (license tag shown on Hugging Face)) |
| Size | 117B parameters, 5.1B active | ~428B parameters, ~23B active |
| Maker says | “production, general purpose, high reasoning use cases” | “MiniMax-M3 is a native multimodal model with 1M context.” |
| 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.
More comparisons