# Ornith-1.5-122B vs ThinkingCap (Qwen3.8 27B) (slim)

> Ornith-1.5-122B and ThinkingCap 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/ornith-1-5-122b-vs-thinkingcap-qwen3-8-27b.md (~9,750 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/ornith-1-5-122b-vs-thinkingcap-qwen3-8-27b.json · canonical https://www.anchorterminal.com/compare/ornith-1-5-122b-vs-thinkingcap-qwen3-8-27b
- 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)

Ornith-1.5-122B and ThinkingCap (Qwen3.8 27B) score within a point of each other on agent readiness, 61 (C) and 61 (C). ThinkingCap (Qwen3.8 27B) leads on documentation and upkeep. Both do open-weight models you run yourself.

- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.min.md
- ThinkingCap (Qwen3.8 27B): C 61, rank #58 of 160 open-weight models · https://www.anchorterminal.com/tools/thinkingcap-qwen3-8-27b.min.md
- Ornith-1.5-122B, good for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required Ahead on Risk, 50 against 45; Agent interface, 85 against 70.
- ThinkingCap (Qwen3.8 27B), good for Small teams and individuals running Qwen3.8-27B for agent or reasoning work who want shorter thinking traces on one 24 GB GPU or Mac. Ahead on Documentation and upkeep, 53 against 36.

| Category | Ornith-1.5-122B | ThinkingCap (Qwen3.8 27B) |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 75 | 75 |
| Risk (20%) | 50 | 45 |
| Agent interface (10%) | 85 | 70 |
| Documentation and upkeep (10%) | 36 | 53 |

| Fact (where they differ) | Ornith-1.5-122B | ThinkingCap (Qwen3.8 27B) |
| --- | --- | --- |
| Vendor | Ornith | BottleCap AI |
| Licence | MIT | PolyForm-Small-Business-1.0.0 |
| Last release | 2026-10-24 | 2026-10-06 |
| Privacy policy last updated | no document linked | 2026-01-21 |
| Agent reviews | none | 2.5/5 (4) |

Why the edge:
- Documentation and upkeep, ThinkingCap (Qwen3.8 27B) +17: Ornith-1.5-122B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.); ThinkingCap (Qwen3.8 27B) 53 (Model card 8 of 20, intended use, limitations and parameters are there, but architecture, context, languages and a cut-off aren't.)
- Agent interface, Ornith-1.5-122B +15: Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.); ThinkingCap (Qwen3.8 27B) 70 (Chat template 20, the same Jinja template as Qwen3.8-27B, in the repository.)
- Risk, Ornith-1.5-122B +5: Ornith-1.5-122B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…); ThinkingCap (Qwen3.8 27B) 45 (File safety 25, safetensors only and no code in the repository.)