Gemini 4 Carbon is now generally available.
It ranks #3 on the Vals Index, about 1pp behind SOTA Fable 5.2, and costs $7 less per test ($10.51 vs $17.94).
It remains #1 on the Finance Index, Legal Research and Tax. https://t.co/DHlkw6bNTH
Gives a cost-versus-accuracy comparison between Gemini 4 Carbon and Fable 5.2 from a third-party benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition →, useful for picking a model for finance, legal and tax workloads.
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
