# gpt-oss-20b vs Step 3.7 Flash (slim)

> gpt-oss-20b scores 69.9 (B) to Step 3.7 Flash's 59.8 (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-20b-vs-step-3-7-flash.md (~9,200 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/gpt-oss-20b-vs-step-3-7-flash.json · canonical https://www.anchorterminal.com/compare/gpt-oss-20b-vs-step-3-7-flash
- 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-20b scores 69.9 (B) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in every scored category. Both do open-weight models you run yourself.

- gpt-oss-20b: B 69.9, rank #8 of 160 open-weight models · https://www.anchorterminal.com/tools/gpt-oss-20b.min.md
- Step 3.7 Flash: C 59.8, rank #93 of 160 open-weight models · https://www.anchorterminal.com/tools/step-3-7-flash.min.md
- gpt-oss-20b, good for Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time Ahead on Reach, 90 against 70; Risk, 85 against 45; Agent interface, 90 against 85.
- Step 3.7 Flash, good for Teams with a GPU server or a provider account that want an open, long-context agent model with vision

| Category | gpt-oss-20b | Step 3.7 Flash |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 70 |
| Risk (20%) | 85 | 45 |
| Agent interface (10%) | 90 | 85 |
| Documentation and upkeep (10%) | 42 | 39 |

| Fact (where they differ) | gpt-oss-20b | Step 3.7 Flash |
| --- | --- | --- |
| Vendor | OpenAI | StepFun |
| Licence | Apache-2.0 | Apache-2.0 (metadata and card; no LICENSE file) |
| Last release | 2025-08-26 | 2026-06-03 |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Risk, gpt-oss-20b +40: gpt-oss-20b 85 (File safety earns 25, since the weights are safetensors and metal/model.bin is OpenAI's own raw Metal format rather than pickle, and nothing in the repository r…); Step 3.7 Flash 45 (File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25).)
- Reach, gpt-oss-20b +20: gpt-oss-20b 90 (Memory earns 25, since OpenAI's own MXFP4 build is 13.76 GB and a fifth on top is 16.5 GB, just past the 16 GB band, and Ollama's 14 GB build lands in the same…); Step 3.7 Flash 70 (Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference m…)
- Agent interface, gpt-oss-20b +5: gpt-oss-20b 90 (The chat template earns 20, a Jinja file in the repository.); Step 3.7 Flash 85 (Chat template 20, chat_template.jinja in the repository (5,723 characters).)