Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Improved Gemini 2.5 Flash and Flash-Lite

developers.googleblog.com

Post reply on HN
Print view View original

51–60 of 285 posts

Re: Improved Gemini 2.5 Flash and Flash-Lite

#51

Post by crishoj »

newfocogi wrote: post #3

Non-AI Summary: Both models have improved intelligence on Artificial Analysis index with lower end-to-end response time. Also 24% to 50% improved output token efficiency (resulting in lower cost). Gemini 2.5 Flash-Lite improvements include better instruction following, reduced verbosity, stronger multimodal & translation capabilities. Gemini 2.5 Flash improvements include better agentic tool use and more token-effici…

Any idea what "output token efficiency" refers to? Gemini Flash is billed by number of input/output tokens, which I assume is fixed for the same output, so I'm struggling to understand how it could result in lower cost. Unless of course they have changed tokenization in the new version?

Re: Improved Gemini 2.5 Flash and Flash-Lite

#52

Post by minimaxir »

simonw wrote: post #46
Liwink wrote: post #5

Gemini 2.5 Flash is an impressive model for its price. However, I don't understand why Gemini 2.0 Flash is still popular. From OpenRouter last week: * xAI: Grok Code Fast 1: 1.15T * Anthropic: Claude Sonnet 4: 586B * Google: Gemini 2.5 Flash: 325B * Sonoma Sky Alpha: 227B * Google: Gemini 2.0 Flash: 187B * DeepSeek: DeepSeek V3.1 (free): 180B * xAI: Grok 4 Fast (free): 158B * OpenAI: GPT-4.1 Mini: 157B * DeepSeek: De…

My one big problem with OpenRouter is that, as far as I can tell, they don't provide any indication of how many companies are using each model. For all I know there are a couple of enormous whales on there who, should they decide to switch from one model to another, will instantly impact those overall ratings. I'd love to have a bit more transparency about volume so I can tell if that's what is happening or not.

Granted, due to OpenRouter's 5.5% surcharge, any enormous whales have a strong financial incentive to use the provider's API directly.

A "weekly active API Keys" faceted by models/app would be a useful data point to measure real-world popularity though.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#53

Post by davidmckayv »

This really captures something I've been experiencing with Gemini lately. The models are genuinely capable when they work properly, but there's this persistent truncation issue that makes them unreliable in practice.

I've been running into it consistently, responses that just stop mid-sentence, not because of token limits or content filters, but what appears to be a bug in how the model signals completion. It's been documented on their GitHub and dev forums for months as a P2 issue.

The frustrating part is that when you compare a complete Gemini response to Claude or GPT-4, the quality is often quite good. But reliability matters more than peak performance. I'd rather work with a model that consistently delivers complete (if slightly less brilliant) responses than one that gives me half-thoughts I have to constantly prompt to continue.

It's a shame because Google clearly has the underlying tech. But until they fix these basic conversation flow issues, Gemini will keep feeling broken compared to the competition, regardless of how it performs on benchmarks.

https://github.com/googleapis/js-genai/issues/707

https://discuss.ai.google.dev/t/gemini-2-5-pro-incomplete-re...

Re: Improved Gemini 2.5 Flash and Flash-Lite

#54

Post by fnordsensei »

Imustaskforhelp wrote: post #32
ChildOfChaos wrote: post #28

Hopefully this isn't instead of the rumoured Gemini 3 pro this week.

I think that the Gemini 3 pro might be next month I am not sure. can I get the sources of your rumour please? (Yes I know that I can search it but I would honestly prefer it if you could share it, thanks in advance!)

Next week is next month.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#55

Post by minimaxir »

koakuma-chan wrote: post #8
Liwink wrote: post #5

Gemini 2.5 Flash is an impressive model for its price. However, I don't understand why Gemini 2.0 Flash is still popular. From OpenRouter last week: * xAI: Grok Code Fast 1: 1.15T * Anthropic: Claude Sonnet 4: 586B * Google: Gemini 2.5 Flash: 325B * Sonoma Sky Alpha: 227B * Google: Gemini 2.0 Flash: 187B * DeepSeek: DeepSeek V3.1 (free): 180B * xAI: Grok 4 Fast (free): 158B * OpenAI: GPT-4.1 Mini: 157B * DeepSeek: De…

Why is Grok so popular

Grok Code Fast 1 usage is driven almost entirely by Kilo Code and Cline: https://openrouter.ai/x-ai/grok-code-fast-1/apps

Both apps have offered usage for free for a limited time:

https://blog.kilocode.ai/p/grok-code-fast-get-this-frontier-...

https://cline.bot/blog/grok-code-fast

Re: Improved Gemini 2.5 Flash and Flash-Lite

#56

Post by zitterbewegung »

bl4ckneon wrote: post #43
zitterbewegung wrote: post #36

Okay this is a nitpick but why wouldn't you increment a part of the version number to signify that there is an improvement? These releases are confusing.

I would assume that it will supersede the model that they currently have. So eventually 2.5 flash will be the new and improved 2.5 Flash rather than 2.6. Same way that openai updated their 4-o models and the like, which didn't turn out so well when it started glazing everyone and they had to revert it (maybe that was just chat and not api)

Even if it was just chat and or API I have used the API and I know that they have at minimum added the retraining date and time that they could just affix to the Gemini 2.5 Flash and Flash-Lite because when I use the API I have to verify that the upgrade of the backend system didn't break anything and pinning versions I assume is pretty common.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#57

Post by minimaxir »

crishoj wrote: post #51
newfocogi wrote: post #3

Non-AI Summary: Both models have improved intelligence on Artificial Analysis index with lower end-to-end response time. Also 24% to 50% improved output token efficiency (resulting in lower cost). Gemini 2.5 Flash-Lite improvements include better instruction following, reduced verbosity, stronger multimodal & translation capabilities. Gemini 2.5 Flash improvements include better agentic tool use and more token-effici…

Any idea what "output token efficiency" refers to? Gemini Flash is billed by number of input/output tokens, which I assume is fixed for the same output, so I'm struggling to understand how it could result in lower cost. Unless of course they have changed tokenization in the new version?

The post implies that the new model are better at thinking, therefore less time/cost spent overall.

The first chart implies the gains are minimal for nonthinking models.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#58

Post by minimaxir »

zzleeper wrote: post #40
minimaxir wrote: post #30

Gemini 2.5 Flash has been the LLM I've used the most recently for a variety of domains, especially image inputs and structured outputs which beat both OpenAI and Anthropic in my opinion.

Not sure prices are changed though. :/

Prices indeed did not change, I misread and deleted.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#59

Post by bogtog »

> Today, we are releasing updated versions of Gemini 2.5 Flash and 2.5 Flash-Lite, available on Google AI Studio and Vertex AI, aimed at continuing to deliver better quality while also improving the efficiency.

Typo in the first sentence? "... improving the efficiency." Gemini 2.5 Pro says this is perfectly good phrasing, whereas ChatGPT and Claude recognize that it's awkward or just incorrect. Hmm...

Re: Improved Gemini 2.5 Flash and Flash-Lite

#60

Post by gpm »

bogtog wrote: post #59

> Today, we are releasing updated versions of Gemini 2.5 Flash and 2.5 Flash-Lite, available on Google AI Studio and Vertex AI, aimed at continuing to deliver better quality while also improving the efficiency. Typo in the first sentence? "... improving the efficiency." Gemini 2.5 Pro says this is perfectly good phrasing, whereas ChatGPT and Claude recognize that it's awkward or just incorrect. Hmm...

"Improving the efficiency" sounds fine to me (a native English speaker), what's wrong with it in your opinion?
Post reply on HN