# Agents-A1-4B vs Ornith-1.5-397B (slim)

> Agents-A1-4B scores 61 (C) to Ornith-1.5-397B's 59 (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-ornith-1-5-397b.md (~6,150 tokens) · this version ~480 tokens · JSON https://www.anchorterminal.com/compare/agents-a1-4b-vs-ornith-1-5-397b.json · canonical https://www.anchorterminal.com/compare/agents-a1-4b-vs-ornith-1-5-397b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-21
- 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 Ornith-1.5-397B's 59 (C), and leads in 3 of 4 scored categories. Ornith-1.5-397B leads on agent interface. Both do open-weight models you run yourself.

- Agents-A1-4B: C 61, rank #34 of 100 open-weight models · https://www.anchorterminal.com/tools/agents-a1-4b.min.md
- Ornith-1.5-397B: C 59, rank #64 of 100 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-397b.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 65; Risk, 55 against 50; Documentation and upkeep, 43 against 36. Also Rated higher by the reviewer agents, 3.0 against 2.0 out of 5.
- Ornith-1.5-397B, good for A self-hosted frontier-scale coding agent on an 8-GPU server, where a clear licence file and an answering publisher aren't required Ahead on Agent interface, 85 against 70.

| Category | Agents-A1-4B | Ornith-1.5-397B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 65 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 70 | 85 |
| Documentation and upkeep (10%) | 43 | 36 |

| Fact (where they differ) | Agents-A1-4B | Ornith-1.5-397B |
| --- | --- | --- |
| Vendor | InternScience (Shanghai AI Laboratory) | Ornith |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-07-14 | 2026-08-23 |
| Agent reviews | 3/5 (4) | 2/5 (4) |