Just updated my HN Wrapped project with it and it does well on my totally unscientific LLM humor benchmark: https://hn-wrapped.kadoa.com
Gemini 3.5 Flash
81–90 of 692 posts
Re: Gemini 3.5 Flash
#82Earlier quoted context omitted.
The boat moves in all three for me
The boat itself rocks, but do you see the background changing to indicate the boat is progressing through the environment? I only see that in the 3.1 Pro example. I believe that's what the OP meant.
I think this illustrates the problem with OP's prompt. If the goal is specifically to implement a scrolling background, this should have been in the prompt.
Re: Gemini 3.5 Flash
#83The price is crazy.
And I guess Gemini 3.5 pro will have the pricing increment, too. 12 x 5 = 60?
It seems like google does want us to use Chinese models.
Re: Gemini 3.5 Flash
#84Per million input/output tokens:
Gemini 2.5 flash: $0.30/$2.50
Gemini 3.0 flash preview: $0.50/$3.00
Gemini 3.5 flash: $1.50/$9.00
Interesting pricing direction. I don't think we have ever seen a 3x price increase for in the immediate next same-sized model (and lol @ 3 only ever getting a preview).
3.5 flash costs similar to Gemini 2.5 pro which was $1.25/$10
Re: Gemini 3.5 Flash
#85Beats 3.1 Pro for price per token, but artificial analysis is showing it's dumber per token and costs more overall
The pricing is an issue.
Re: Gemini 3.5 Flash
#86Earlier quoted context omitted.
Don’t let that fool yourself. Google will have SOTA models as big as or even bigger than their competitors. They are just refining their current models while they finish training the next generation. They will all come out at about the same time. Anthropic, OpenAi, Google, xAI
Anthropic has been sitting on Mythos for a while now. I guess they don't feel pressured to fuck it ship it until anyone else gets a 10T to work.
According to people who have access to Mythos, it is slightly worse than GPT-5.5-xhigh. At least for security tasks.
Hold on, I think this claim needs some hard data. Here you go gentlemen:
https://www.aisi.gov.uk/blog/our-evaluation-of-openais-gpt-5...
Re: Gemini 3.5 Flash
#87Engineers at google have publically stated that the models are too big and are far from their potencial. Glad they're being proven right with every release. They continue to focus on smaller models while openai and anthropic are increasing compute requirements for their SOTA models.
> Engineers at google have publically stated that the models are too big and are far from their potencial
Can you link to a source?
Re: Gemini 3.5 Flash
#88Is there a good benchmark tracking hallucinations? The models are all incredibly good now, even the open ones, and my hope is that the rate of hallucinations is something that's falling off in concert with larger and larger context lengths.
well there is https://artificialanalysis.ai/evaluations/omniscience
It's a gibberish input detection benchmark, and does not measure output hallucinations.
Re: Gemini 3.5 Flash
#89Beats 3.1 Pro for price per token, but artificial analysis is showing it's dumber per token and costs more overall
Arena.ai is saying "Gemini 3.5 Flash’s pricing shifts the Pareto frontier in Text. 8 models from GoogleDeepMind dominate the Text Arena Pareto curve where only 4 labs are represented for top performance in their price tiers."
Re: Gemini 3.5 Flash
#90Conspiracy theory:
This model isnt an advancement, its a previous model that runs more compute, which is why it costs more