# Recursive Flint vs Step 3.7 Flash (slim)

> Recursive Flint 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/recursive-flint-vs-step-3-7-flash.md (~9,750 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/recursive-flint-vs-step-3-7-flash.json · canonical https://www.anchorterminal.com/compare/recursive-flint-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)

Recursive Flint scores 61 (C) 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.

- Recursive Flint: C 61, rank #54 of 160 open-weight models · https://www.anchorterminal.com/tools/recursive-flint.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
- Recursive Flint, good for Agents doing repository work on a 32 to 48 GB Mac or NVIDIA box that want a sparse coder with documented tool calls and a plain licence. Ahead on Reach, 85 against 70; Risk, 60 against 45; Agent interface, 90 against 85; Documentation and upkeep, 67 against 39.
- 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 | Recursive Flint | Step 3.7 Flash |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 70 |
| Risk (20%) | 60 | 45 |
| Agent interface (10%) | 90 | 85 |
| Documentation and upkeep (10%) | 67 | 39 |

| Fact (where they differ) | Recursive Flint | Step 3.7 Flash |
| --- | --- | --- |
| Vendor | Recursive | StepFun |
| Licence | Apache-2.0 | Apache-2.0 (metadata and card; no LICENSE file) |
| Last release | 2026-10-21 | 2026-06-03 |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Documentation and upkeep, Recursive Flint +28: Recursive Flint 67 (Model card 17 of 20, everything but languages.); Step 3.7 Flash 39 (Model card 14, Intended use, the architecture, the parameters, the context and the language (in the metadata) are on the card.)
- Reach, Recursive Flint +15: Recursive Flint 85 (Memory 20 of 30, Recursive's MLX INT4 build is 22.6 GB, or 27.1 GB with a fifth added, which fits 32 GB, and every other 4-bit build lands in the same band.); 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…)
- Risk, Recursive Flint +15: Recursive Flint 60 (File safety 15 of 25, safetensors and GGUF only, but the card's documented BF16 route installs the wheel shipped in the repository.); Step 3.7 Flash 45 (File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25).)
- Agent interface, Recursive Flint +5: Recursive Flint 90 (Chat template 20, a Jinja file in the repository and inside both GGUFs.); Step 3.7 Flash 85 (Chat template 20, chat_template.jinja in the repository (5,723 characters).)