Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Engines

Engine overview

How the models are run and tested – split into model servers (inference engines) and harness runtimes.

⚙️ Inference

Model servers (4)

Engines that serve the model – average throughput per server.

llama.cpp
251,8 tok/s Ø
3089 Läufe · 62 Modelle · Max 2.491,2
vLLM
265,9 tok/s Ø
739 Läufe · 50 Modelle · Max 1.608,5
colibri
0,0 tok/s Ø
3 Läufe · 1 Modelle · Max 0,0
llm
19,5 tok/s Ø
1 Läufe · 1 Modelle · Max 19,5
🚀 Harness

Harness runtimes (2)

Test runtimes for agent/chat benchmarks – average success rate.

GodClaw
56 % Ø
16 Läufe · 5 Modelle · Max 87%
OpenClaw CLI
53 % Ø
14 Läufe · 4 Modelle · Max 91%
🖥️ Operating systems

Operating systems (3)

These OS platforms the benchmarks were measured on – click for a landing page per operating system.

🖥️Ubuntu 26.04 LTS (Kernel 7.0.0-27-generic)1 Boards · 27 Modelle · 104 Läufe🖥️Ubuntu 24.04.2 LTS (Kernel 6.17.0-40-generic)1 Boards · 2 Modelle · 2 Läufe🖥️Ubuntu 24.04.3 LTS (Kernel 7.0.0-28-generic)1 Boards · 1 Modelle · 1 Läufe