Best Model for Openclaw (WildClaw Benchmarks!)

Claude Opus tops the WildClaw benchmark at 51% — but the $80 run cost makes GPT-5.4 and Mimo V2 the real winners for cheap agents.

## The Benchmark Setup WildClaw runs real agentic tasks (reading emails, launching tasks) inside Dockerized OpenClaw containers — not a software-engineering coding test. The suite is open source, so you can clone it, modify tests, and rerun on your own models. Creator's caveat: "it might be the case that the reliability of these tests might not be super good in the future as companies optimize specifically for this benchmark."

## Top Scores And Costs - Claude Opus: 51% overall, $80 to run the full suite — "the cost is very very high." - GPT-5.4: close second at roughly a quarter of Opus's cost, faster too. Many users are switching to it because the Claude Opus coding-plan limits were recently cut, forcing more API spend. - Mimo V2 (Xiaomi): scored high at a $26 run cost. Free extended access available for ~6 more days via Kilo Code and partner providers. - Minimax 2.7: used internally on Loki/Gambit agents for two months; real-world drop-off vs Opus is visible but cost is "really really cheap." - Grok: full suite completed in 94 minutes vs ~500 minutes — "almost five times faster."

## GLM5.1 Still Running GLM5 released two days before the video; creator is mid-test on GLM 5.1 because "they tune themselves for agentic use case" and claim 90% of Opus. He couldn't finish in time for the video since GLM5 is "a bit slow."

## Coding Plans Beat Token Plans Creator runs his agents on a MiniMax coding plan rather than token plans — "I don't want to fix and play with my open claw all the time." Generous flat-rate limits beat per-token optimization when the model flaps.

## Bottom Line Use Opus only if you have an uncapped coding plan. Otherwise run WildClaw yourself against GPT-5.4, Mimo V2, or Grok and pick the one that passes your own tasks for the lowest $/run.