VulcanBench founder hits Muse Wonder's usage limits before finishing a benchmark

Morgan Linton says Muse Code limits stopped a full VulcanBench run, raising an early cost-per-task question for Meta's new coding model.

By · Published · Updated

Primary source: X

Why it matters

Linton's test raises a purchasing question for teams considering Meta's agent claims: how much useful engineering work fits inside a model's usage allowance? A full cost-per-task comparison will matter more than a token price or a single early run.

Morgan (@morganlinton): Out of the gate, I am finding Muse Wonder to be a very expensive model to use. At Low Effort, I hit my weekly usage limit on my Muse Code pl (2-post thread) — Out of the gate, I am finding Muse Wonder to be a very…

Morgan Linton, founder of the open-source coding benchmark VulcanBench, says he exhausted Muse Code's weekly usage allowance before he could finish a full benchmark run of Meta's new Muse Wonder model. His October 13th account came a day after Meta launched Muse Wonder and Muse Wonder Full, putting the model's cost in focus before Linton had completed a comparable evaluation.…

Reader comments

Conversation for this story loads after sign-in.