# gpt-oss

> OpenAI's open-weight reasoning models.

gpt-oss has a SharkScore of 63.5/100, ranked #4 of 8 in Models (updated 2026-11-17).

- Website: https://openai.com/open-models (openai.com)
- Kind: Model · Pricing: Open source
- Maker: OpenAI
- Repository: https://github.com/openai/gpt-oss
- Categories: Models
- Verified by the maker: no

## Why it scores 63.5

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 70 | 30% |
| User reviews | 81 | 25% |
| Maintenance | 55 | 20% |
| Trust & transparency | 60 | 15% |
| Momentum | 22 | 10% |

Evidence covers 100% of the score's weight. Compared with other listings in Models.

## Evidence

| Signal | Value |
|---|---|
| Monthly visits | — |
| GitHub stars | 19K |
| Stars, last 90 days | +900 |
| Downloads, 30 days | 7M |
| Reviews | 4.2 stars from 28 |
| Last update | 60 days ago |
| Uptime, 30 days | — |
| Public pricing / Free tier / API / MCP | yes / yes / no / no |

## Top alternatives

1. [Qwen](https://rankshark.pro/tools/qwen) — SharkScore 79.5. Alibaba's open models for text, code, vision and audio.
2. [DeepSeek](https://rankshark.pro/tools/deepseek) — SharkScore 73.8. Open-weight reasoning and chat models.
3. [Llama](https://rankshark.pro/tools/llama) — SharkScore 64.6. Meta's family of open-weight language models.
4. [Ollama](https://rankshark.pro/tools/ollama) — SharkScore 83.9. Run open models on your own computer.
5. [Hugging Face](https://rankshark.pro/tools/hugging-face) — SharkScore 83.1. The home of open models, datasets and Spaces.

---
Source: https://rankshark.pro/tools/gpt-oss · Method v2026-11-17.1: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
