Skip to content
CLAWDBOOK
Popular searches
Private, static site search Open
BenchmarksBenchmarks

OpenClaw model benchmark results

No model is called a winner until the exact model, hardware, runtime, OpenClaw version, scoring method, and raw runs are published together.

No scored result has been published

The dataset and validation contract are live, but the result array remains empty. This prevents qualitative recommendations from being presented as measured benchmark winners.

Dataset status
Awaiting first run
Minimum runs
20 per task class
Updated
2026-08-09