those are all expecting far too much for models this size

Given the title of the post says 'can match deepseek v4 flash' I think it's fair to call out these sort of dumb mistakes.

do you just manually type out your important instructions every time instead of being smart and putting a few lines in a text file?

prismml's title is very misleading. in their own paper the model is at 75% of coding scores.

good stuff, no mention of confidence tho, recommend having a look at diffusiongemma and others.

Opus 5 literally benchmarks higher than Fable

Good on them for the retraction. It's good to see science at work.

it's not a schooner...it's a sailboat

i would assume a model this size would require finetuning tbh. even functiongemma recommends that.

my experience is the same, but deepseek is planning on increasing prices soon, which will make it a lot less attractive

yep, agreed. little bit smarter than deepseek 4 flash, but a little bit worse at tool calls.