Post

So the tokens are cheaper but it takes more thinking tokens to get the same result on the benchmark so the cost to run the benchmark is higher?

0 reposts0 likes

Ok, yeah looking at the AA results. Gemini 3.5 Flash high took 73M tokens to get a score of 55, Opus 4.7 high took 12M tokens to get a score of 52 and Opus 4.7 max took 110M tokens to get a score of 57