Hacker News

points by pcwelder 15 hours ago | 0 comments

Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers and we used the hell out of them.

Since then none of the Google models have competed well with the others at their price points. Long context performance drop, instruction following issues, unnecessarily complex and sloppish outputs.

Argon is no different, it feels just an iteration better than 3.8 flash. I don't trust the AA ranking yet.

[–] timabdulla 15 hours ago

I agree. Flash 3.8 is not good and actually quite expensive, given its tendency to overthink everything. We've been transitioning lots of workloads that were formerly on Flash to Haiku 5.5. Great model.

[–] ashu1461 15 hours ago

Even with gemini 2.5 or so i remember the models used to just simply hang in production and randomly used to collate tokes and give in the output stream vs giving one by one which was weird.

Also the guardrails were implemented in a very bad manner. By default the models used to raise a default guardrail error on basic queries.

[–] bearjaws 15 hours ago

250tk/s is really the sweet spot for chat IMO, results from Flash were fast and usually good quality.

[–] kilroy123 13 hours ago

Gemini 2.5 flash was amazing via the API for a lot of use cases. Great blend of fast, accurate, and cheap.