# Agents-A1-4B vs Step 3.7 Flash (slim)

> Agents-A1-4B scores 61 (C) 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/agents-a1-4b-vs-step-3-7-flash.md (~9,050 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/agents-a1-4b-vs-step-3-7-flash.json · canonical https://www.anchorterminal.com/compare/agents-a1-4b-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)

Agents-A1-4B scores 61 (C) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in 3 of 4 scored categories. Step 3.7 Flash leads on agent interface. Both do open-weight models you run yourself.

- Agents-A1-4B: C 61, rank #39 of 160 open-weight models · https://www.anchorterminal.com/tools/agents-a1-4b.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
- Agents-A1-4B, good for Local agent loops (search, research, tool calls) on a laptop, a small GPU or a phone-class machine, under a plain licence Ahead on Reach, 90 against 70; Risk, 55 against 45.
- 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 Ahead on Agent interface, 85 against 70.

| Category | Agents-A1-4B | Step 3.7 Flash |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 70 |
| Risk (20%) | 55 | 45 |
| Agent interface (10%) | 70 | 85 |
| Documentation and upkeep (10%) | 43 | 39 |

| Fact (where they differ) | Agents-A1-4B | Step 3.7 Flash |
| --- | --- | --- |
| Vendor | InternScience (Shanghai AI Laboratory) | StepFun |
| Licence | Apache-2.0 | Apache-2.0 (metadata and card; no LICENSE file) |
| Last release | 2026-07-14 | 2026-06-03 |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Reach, Agents-A1-4B +20: Agents-A1-4B 90 (Memory 30, InternScience's Q4_K_M GGUF with its vision projector is 3.4 GB and needs about 4.1 GB with the fifth added.); 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, Step 3.7 Flash +15: Agents-A1-4B 70 (Chat template 20, a Jinja file in the repository.); Step 3.7 Flash 85 (Chat template 20, chat_template.jinja in the repository (5,723 characters).)
- Risk, Agents-A1-4B +10: Agents-A1-4B 55 (File safety 25, safetensors and GGUF only and nothing from the repository runs.); Step 3.7 Flash 45 (File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25).)