VulcanBench(@VulcanBench):Ruh roh, Muse Wonder could be the most expensive model to benchmark that we've ever come across. The cost-per-task is looking incredibly high 😮 🍉 And this is also why it's soooooo important to not just show accuracy. It's the combination of accuracy and cost-per-task that matters if you want to pick a model for daily use.

2026.10.13 10:09

Ruh roh, Muse Wonder could be the most expensive model to benchmark that we've ever come across. The cost-per-task is looking incredibly high 😮 🍉 And this is also why it's soooooo important to not just show accuracy. It's the combination of accuracy and cost-per-task that matters if you want to pick a model for daily use.

Morgan@morganlinton

2026.10.13 10:07

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 plan in less than 12 hours. With VulcanBench, I couldn't get through an entire effort level run without hitting my limits. Compare this to even something like Astra, which did every effort level, in under 12 hours, for less than $50. That makes Muse Wonder more expensive, and a lot slower, than Astra. Now I'm not sure what to do. I'll either needs to pay a small fortune to benchmark this model given how token hungry it is, or take a month or longer benchmarking it. Put together some preliminary results comparing Muse Wonder to Opus 5.5 and GPT 6.1 Sol w/respect to token use. While it's looking like an accurate model, I care a lot about cost-per-task, as we all should, and right now, this number is looking very high.