# llama.cpp vs Underdog (slim)

> llama.cpp has a score of 60.2 (C) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is agent ergonomics, 58 points. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.md (~1,800 tokens) · this version ~330 tokens · JSON https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.json · canonical https://www.anchorterminal.com/compare/llama-cpp-vs-underdog
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

llama.cpp has a score of 60.2 (C) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is agent ergonomics, 58 points.

- llama.cpp: C 60.2, rank #253 of 452 · https://www.anchorterminal.com/tools/llama-cpp.min.md
- Underdog: F 29.9, rank #444 of 452 · https://www.anchorterminal.com/tools/underdog.min.md
- Pick llama.cpp for reliability (+31), schema & documentation (+23), agent ergonomics (+58), security & auth (+38), maintenance & community (+25), transparency & trust (+36). Pick Underdog for nothing in particular.

| Category | llama.cpp | Underdog |
| --- | --- | --- |
| Reliability (16%) | 64 | 33 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 47 | 24 |
| Agent ergonomics (13%) | 73 | 15 |
| Security & auth (14%) | 52 | 14 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 81 | 56 |
| Transparency & trust (7%) | 60 | 24 |