# MiMo-V2.6-Flash-RL vs Ornith-1.5-9B (slim)

> MiMo-V2.6-Flash-RL and Ornith-1.5-9B 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-ornith-1-5-9b.md (~9,450 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-ornith-1-5-9b.json · canonical https://www.anchorterminal.com/compare/mimo-v2-6-flash-rl-vs-ornith-1-5-9b
- 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 Ornith-1.5-9B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-9B leads on reach and risk. 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
- Ornith-1.5-9B: C 61, rank #51 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-9b.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 Ahead on Documentation and upkeep, 59 against 31.
- Ornith-1.5-9B, good for Local coding and terminal agents on a laptop or a single consumer GPU, where a clear licence file and an answering publisher aren't required Ahead on Reach, 95 against 65; Risk, 50 against 45.

| Category | MiMo-V2.6-Flash-RL | Ornith-1.5-9B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 95 |
| Risk (20%) | 45 | 50 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 59 | 31 |

| Fact (where they differ) | MiMo-V2.6-Flash-RL | Ornith-1.5-9B |
| --- | --- | --- |
| Vendor | Xiaomi (MiMo team) | Ornith |
| Licence | MIT (metadata only, no LICENSE file) | MIT |
| Last release | 2026-10-28 | 2026-08-23 |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- Reach, Ornith-1.5-9B +30: 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.); Ornith-1.5-9B 95 (Memory 30, since Ornith's own MLX 4-bit build is 5.0 GB and needs about 6.0 GB with the fifth added, and its Q4_K_M GGUF and Ollama's build fit 16 GB too.)
- Documentation and upkeep, MiMo-V2.6-Flash-RL +28: 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.); Ornith-1.5-9B 31 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.)
- Risk, Ornith-1.5-9B +5: 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).); Ornith-1.5-9B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories, so the card's --trust-remote-code flag loads nothing from the repositor…)