Comment by hmate9
13 hours ago
It is more expensive per task than 5.6-sol high: https://artificialanalysis.ai/models/gemini-3-8-flash#price-...
13 hours ago
It is more expensive per task than 5.6-sol high: https://artificialanalysis.ai/models/gemini-3-8-flash#price-...
Cheaper at medium level while still being same score as Sol medium
Huh, according to some of those charts, it's both dumber, and more expensive to run against their benchmarking tasks than Fable??? Seems crazy to me.
Perhaps the model is able to evaluate that it's not done, and to keep pressing on in the face of mounting failures, until it eventually arrives at a solution. Where Fable can skip that.
Sol is still underrated imo, especially for the current discounted price