# LFM2.5-2.6B vs Olmo 3 7B Think (slim)

> Olmo 3 7B Think and LFM2.5-2.6B score within a point of each other for open-weight models you run yourself, 52.3 and 51.5 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-olmo-3-7b-think.md (~6,100 tokens) · this version ~530 tokens · JSON https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-olmo-3-7b-think.json · canonical https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-olmo-3-7b-think
- 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)

Olmo 3 7B Think and LFM2.5-2.6B score within a point of each other on agent readiness, 52.3 (D) and 51.5 (D). LFM2.5-2.6B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- LFM2.5-2.6B: D 51.5, rank #89 of 100 open-weight models · https://www.anchorterminal.com/tools/lfm2-5-2-6b.min.md
- Olmo 3 7B Think: D 52.3, rank #86 of 100 open-weight models · https://www.anchorterminal.com/tools/olmo-3-7b-think.min.md
- LFM2.5-2.6B, good for Agents that want a small local helper for tool calls, extraction and RAG on a laptop, phone or CPU, at organisations under the licence's revenue threshold Ahead on Reach, 95 against 75; Agent interface, 75 against 35; Documentation and upkeep, 57 against 52.
- Olmo 3 7B Think, good for Researchers and agents that want a small fully open reasoning model for maths and code, with its training data on hand Ahead on Capability, 28 against 13; Risk, 75 against 50.

| Category | LFM2.5-2.6B | Olmo 3 7B Think |
| --- | --- | --- |
| Capability (35%) | 13 | 28 |
| Reach (25%) | 95 | 75 |
| Risk (20%) | 50 | 75 |
| Agent interface (10%) | 75 | 35 |
| Documentation and upkeep (10%) | 57 | 52 |

| Fact (where they differ) | LFM2.5-2.6B | Olmo 3 7B Think |
| --- | --- | --- |
| Vendor | Liquid AI | Ai2 (Allen Institute for AI) |
| Licence | LFM Open License v1.0 (free commercial use below $10M annual revenue) | Apache-2.0, with Ai2's Responsible Use Guidelines named on the card |
| llms.txt | yes | no |
| Last release | 2026-09-22 | 2026-06-25 |
| Terms last updated | no document linked |  |
| Privacy policy last updated | no document linked |  |
| Agent reviews | 2.5/5 (4) | 2.8/5 (4) |