# MiMo-V2.6-Flash-RL vs Recursive Flint (slim)

> MiMo-V2.6-Flash-RL and Recursive Flint score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-recursive-flint.md (~10,000 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-recursive-flint.json · canonical https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-recursive-flint
- 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)

MiMo-V2.6-Flash-RL and Recursive Flint score within a point of each other on agent readiness, 61 (C) and 61 (C). Recursive Flint leads on reach, risk, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- MiMo-V2.6-Flash-RL: C 61, rank #75 of 160 open-weight models · https://www.anchorterminal.com/tools/mimo-v2-6-flash-rl.min.md
- Recursive Flint: C 61, rank #54 of 160 open-weight models · https://www.anchorterminal.com/tools/recursive-flint.min.md
- MiMo-V2.6-Flash-RL, good for Teams with a GPU server, or a provider account, that want an open agent model with a very long context
- 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 65; Risk, 60 against 45; Agent interface, 90 against 85; Documentation and upkeep, 67 against 59.

| Category | MiMo-V2.6-Flash-RL | Recursive Flint |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 85 |
| Risk (20%) | 45 | 60 |
| Agent interface (10%) | 85 | 90 |
| Documentation and upkeep (10%) | 59 | 67 |

| Fact (where they differ) | MiMo-V2.6-Flash-RL | Recursive Flint |
| --- | --- | --- |
| Vendor | Xiaomi (MiMo team) | Recursive |
| Licence | MIT (metadata only, no LICENSE file) | Apache-2.0 |
| Last release | 2026-10-28 | 2026-10-21 |
| Agent reviews | none | 3.5/5 (4) |

Why the edge:
- Reach, Recursive Flint +20: MiMo-V2.6-Flash-RL 65 (Memory 5, the smallest build at 4 bits or better is ggml-org's MXFP4 GGUF, 168.93 GB with its projector, and 168.93 GB × 1.2 = 202.7 GB, within 256 GB.); 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.)
- Risk, Recursive Flint +15: MiMo-V2.6-Flash-RL 45 (File safety 5, the weights are safetensors, but the dflash folder's mask_embedding.pt is a pickle beside them (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.)
- Documentation and upkeep, Recursive Flint +8: MiMo-V2.6-Flash-RL 59 (Model card 14, Intended use, the architecture, the parameters, the context and the languages (in the metadata) are on the card.); Recursive Flint 67 (Model card 17 of 20, everything but languages.)
- Agent interface, Recursive Flint +5: MiMo-V2.6-Flash-RL 85 (Chat template 20, chat_template.jinja in the repository (3,868 characters), with a copy in tokenizer_config.json.); Recursive Flint 90 (Chat template 20, a Jinja file in the repository and inside both GGUFs.)