# gpt-oss-120b vs ZAYA1-8B (slim)

> gpt-oss-120b scores 70.2 (BB) to ZAYA1-8B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/gpt-oss-120b-vs-zaya1-8b.md (~8,950 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/gpt-oss-120b-vs-zaya1-8b.json · canonical https://www.anchorterminal.com/compare/gpt-oss-120b-vs-zaya1-8b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

gpt-oss-120b scores 70.2 (BB) on agent readiness against ZAYA1-8B's 61 (C), and leads in 2 of 4 scored categories. ZAYA1-8B leads on reach and documentation and upkeep. Both do open-weight models you run yourself.

- gpt-oss-120b: BB 70.2, rank #6 of 160 open-weight models · https://www.anchorterminal.com/tools/gpt-oss-120b.min.md
- ZAYA1-8B: C 61, rank #85 of 160 open-weight models · https://www.anchorterminal.com/tools/zaya1-8b.min.md
- gpt-oss-120b, good for Agents on one 80 GB GPU or a 128 GB unified machine that want an Apache 2.0 reasoning model with wide runtime support Ahead on Risk, 95 against 55; Agent interface, 90 against 60. Also Agent-ready, a grade of BB or better.
- ZAYA1-8B, good for People who want a small, fast reasoning model for maths and code and can live without tool calling Ahead on Reach, 80 against 75; Documentation and upkeep, 50 against 45.

| Category | gpt-oss-120b | ZAYA1-8B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 80 |
| Risk (20%) | 95 | 55 |
| Agent interface (10%) | 90 | 60 |
| Documentation and upkeep (10%) | 45 | 50 |

| Fact (where they differ) | gpt-oss-120b | ZAYA1-8B |
| --- | --- | --- |
| Vendor | OpenAI | Zyphra |
| Last release | 2025-08-26 | 2026-07-02 |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Risk, gpt-oss-120b +40: gpt-oss-120b 95 (File safety earns 25, safetensors only, with metal/model.bin a raw format and not pickle, and nothing from the repository runs on load.); ZAYA1-8B 55 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)
- Agent interface, gpt-oss-120b +30: gpt-oss-120b 90 (The chat template earns 20, a Jinja file in the repository.); ZAYA1-8B 60 (Chat template 20, chat_template.jinja in the repository (10,700 characters).)
- Reach, ZAYA1-8B +5: gpt-oss-120b 75 (Memory earns 10, because the smallest 4-bit build, Ollama's 65 GB gpt-oss:120b, needs about 78 GB with the fifth added, which fits the reference machine but not…); ZAYA1-8B 80 (Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 GB, within 16 GB.)
- Documentation and upkeep, ZAYA1-8B +5: gpt-oss-120b 45 (The model card earns 20, with all seven items in OpenAI's arXiv card.); ZAYA1-8B 50 (Model card 5, Intended use and the parameter counts are on the card.)