I did some tests with heavily math oriented programming using ChatGPT and Gemini to rubber-duck (not agentic), going over C performance tuning, checking C code for possible optimizations, going over math oriented code and number theory, and working on optimizing threading, memory throughput, etc. to make the thing go faster, then benchmarking runs of the updated code. Gemini was by far better than ChatGPT in this domain. I was able to test changes by benchmarking. For my use case it was night and day, Gemini's advice generally quite strong and was useful to significantly improve benchmarked performance, ChatGPT was far less useful for this use case. What will work for you will depend on your use case, how well your prompting is tuned to the system you're using, and who knows what other factors, but I have a lot of benchmarks that are clear evidence of the opposite of your experience.
Which models? It's completely uninformative to say you compared "ChatGPT" and "Gemini." Those are both just brand names under which several different models are offered, ranging from slow-witted to scary-smart.
It seems to me like this is yet another instance of just reading vibes, like when GPT 5 was underwhelming and people were like "AI is dead", or people thinking Google was behind last year when 2.5 pro was perfectly fine, or overhyping stuff that makes no sense like Sora.
Wasn't the consensus that 3.0 isn't that great compared to how it benchmarks? I don't even know anymore, I feel I'm going insane.
I feel like Gemini made a giant leap forward in its coding capabilities and then in the past week or so it's become shit again - constantly dropping most of the code from my program when I ask it to add a feature - it's gone from incredible to basically useless.
The best decision for Google happened like 10 years ago when they started manufacturing their own silicon for crunching neural nets. No matter if they had a really good crystal ball back then, smart people, time travel machine or just luck, it pays for them now. They don't need to participate in that Ponzi scheme that OpenAI, Nvidia and Microsoft created, and they don't need to wait in line to buy Nvidia cards.
> Naina Raisinghani, 00 needed a name for the new tool to complete the upload. It was 2:30 a.m., though, and nobody was around. So she just made one up, a mashup of two nicknames friends had given her: Nano Banana.
Ah, that explains the silly name for such an impressive tool. I guess it's more a more Googley name than what would have otherwise been chosen: Google Gemini Image Pro Red for Workspace.
Google, OpenAI, and Microsoft all have a very confusing product naming strategy where it’s all lumped under Gemini/ChatGPT/Copilot, and the individual product names are not memorable and really quite obscure. (What does Codex do again?)
Nano Banana doesn’t tell you what the product does, but you sure remember the name. It really rolls off the tongue, and it looks really catchy on social media.
I don't get the Gemini 3 hype... yes it's their first usable model, but its not even close to what Opus 4.5 and GPT 5.2 can do.
Maybe on Benchmarks... but I'm forced to use Gemini at work everyday, while I use Opus 4.5 / GPT 5.2 privately every day... and Gemini is just lacking so much wit, creativity and multi-step problem solving skills compared to Opus.
Not to mention that Gemini CLI is a pain to use - after getting used to the smoothness of Claude
Code.
You’re not alone. I do a small blog reviewing LLMs and have detailed comparisons that go beyond personal anecdotes. Gemini struggles in many usecases.
Everyone has to find what works for them and the switching cost and evaluation cost are very low.
I see a lot of comments generally with the same pattern “i cancelled my LEADER subscription and switched to COMPETITOR”… reminiscent of astroturf. However I scanned all the posters in this particular thread and the cancellers do seem like legit HN profiles.
Claude opus is absurdly amazing. I now spent around $100-200 a day using it. Gemini and all the OpenAI models can’t me up right now.
Having said that, Google are killing it at the image editing right now. Makes me wonder if that’s because of some library of content and once Anthropocene acquires the same they’ll blow us away there too.
I also get weirdly agitated by this. In my mind Geminy 3 is case of clear benchmaxing and over all massive flop.
I am currently testing different IDEs including Antigravity, and I avoid that model at all cost. I will rather pay to use different model, than use Geminy 3.
It sucks at coding compared to OpenAI and Anthropic models and it is not clearly better as chat-bot (I like the context window). The images are best part of it as it is very steerable and fast.
But WTF? This was supposed to be the OpenAI killer model? Please.
People get used to a model and then work best with that model.
If you hand an iPhone user an Android phone, they will complain that Android is awful and useless. The same is true vice versa.
This is in large part why we get so many conflicting reports of model behavior. As you become more and more familiar with a model, especially if it is in fact a good model, other good models will feel janky and broken.
gemini 2.0 flash is and was a godsend for many small tasks and ocr.
There needs to be a greater distinction between models used for human chat, programming agents, and software-integration - where at least we benefitted from gemini flash models.
Nope be it in coding context but Claude and Codex are a combo that really shine and Gemini is pretty useless. The only thing I actually use it for is to triple check the specifications sometimes and thats pretty much it.
This may sound backwards, but gemini 3 flash is quite good when given very specific tasks. It's very fast (much faster than Opus and GPT-5.2), follows instructions very well and spits out working code (in contrast to other flash, haiku etc fast models).
It does need a solid test suite to keep it in check. But you can move very fast if you have well defined small tasks to give it. I have a PRD then breakdown epics, stories and finally the tasks with Pro first. Works very well.
The Gemini voice app on iOS is unimpressive. They force the answers to be so terse to save cost that it’s almost useless. It quickly goes in circles and needs context pruning. I haven’t tried a paid subscription for Gemini CLI or whatever their new shiny is but codex and Claude code have become so good in the last few months that I’m more focused on using them than exploring options.
I've found that for any sort of reasonable task, the free models are garbage and the low-tier paid models aren't much better. I'm not talking about coding, just general "help me" usage. It makes me very wary of using these models for anything that I don't fully understand, because I continually get easily falsifiable hallucinations.
Today, I asked Gemini 3 to find me a power supply with some spec; AC/DC +/- 15V/3A. It did a good job of spec extraction from the PDF datasheets I provided, including looking up how the device performance would degrade using a linear vs switch-mode PSU. But then it comes back with two models from Traco that don't exist, including broken URLs to Mouser. It did suggest running two Meanwell power supplies in series (valid), but 2/3 suggestions were BS. This sort of failure is particularly frustrating because it should be easy and the outputs are also very easy to test against.
Perhaps this is where you need a second agent to verify and report back, so a human doesn't waste the time?
It's prove of what investors have been fearing. That LLMs are a dime a dozen, that there is no real moat and that the products are hence becoming commoditised.
If you can replace one model with another without noticing a huge difference, there can only be a pricing race to the bottom for market share with hence much lower potential profits than the AI bubble has priced in.
I would add that openai is doing such a poor job at every aspect.
Before this gpt nonsense they were such an aspiration for a better world. They quickly turned around, slayer core people from its structure and solely focus on capitalising that they seem to be stuck on dead waters.
Is Gemini 3 still having all these bugs in the software around it? The model is great, but I had all these little bugs (billing issues, attachment not accesible by the model, countless other issues).
Then there is the CLI; I always got "model is overloaded" errors even after trying weekly for a while. I found Google has this complex priority system; their bigger customers get priority (how much you spend determines queue prio).
Anybody did some serious work with gemini-cli? Is it at Opus level?
All of this seems like manufactured hype for Gemini. I use GPT-5.2, Opus 4.5, and Gemini 3 flash and pro with Droid CLI and Gemini is consistently the worst. It gets stuck in loops, wants to wipe projects when it can’t figure out the problem, and still fails to call tools consistently (sometimes the whole thread is corrupted and you can’t rewind and use another model).
Terminal Bench supports my findings, GPT-5.2 and Opus 4.5 are consistently ahead. Only Junie CLI (Jetbrains exclusive) with Gemini 3 Flash scores somewhat close to the others.
It’s also why Ampcode made Gemini the default model and quickly back tracked when all of these issues came to light.
Gemini CLI is too slow to be useful, kind of surprised it was even offered and marketed given how painful it is to use. I thought it'd have to be damaging to the Gemini brand to get people to try it out, suffer painful UX then immediately stop using it. (Using it from Australia may also contribute to its slow perf)
Antigravity was also painful to use at launch where more queries failed then succeeded, however they've basically solved that now to the point where it's become my most used editor/IDE where I've yet to hit a quota limit, despite only being on the $20/mo plan - even when using Gemini 3 Pro as the default model. I also can't recall seeing any failed service responses after a month of full-time usage. It's not the fastest model, but very happy with its high quality output.
I expected to upgrade to a Claude Code Max plan after leaving Augment Code, but given how good Antigravity is now for its low cost, I've switched to it as my primary full-time coding assistant.
Still paying for GitHub Copilot / Claude Pro for general VS Code and CC terminal usage, but definitely getting the most value of out my Gemini AI Pro sub.
Note this is only for development, docs and other work product. For API usage in products, I primarily lean on the cheaper OSS chinese models, primarily MiniMax 2.1 for tool calling or GLM 4.7/KimiK2/DeepSeek when extra intelligence is needed (at slower perf). Gemini Flash for analyzing Image, Audio & PDFs.
Also find Nano Banana/Pro (Gemini Flash Image) to consistently generate the highest quality images vs GPT 1.5/SDXL,HiDream,Flux,ZImage,Qwen, which apparently my Pro sub includes up to 1000/day for Nano Banana or 100/day for Pro?? [1], so it's hard to justify using anything else.
If Gemini 3 Pro was a bit faster and Flash a bit cheaper (API Usage), I could easily see myself switching to Gemini for everything. If future releases get smarter, faster whilst remaining aggressively priced, in the future - I expect I will.
Google can afford to run Gemini for a looong time without any ads, while OpenAI needs necessarily to bring in some revenue: So OpenAI will have to do something (or they believe they can raise money infinitely)
Google can easily give Gemini without Ads to the users for the next 3 - 4 years, forcing OpenAI to cripple their product earlier with Ads because of the need for any revenue
I think Google & Antropic will be one of the two winners; not sure about OpenAI, Perplexity & Co - maybe OpenAI will somehow merge with Microsoft?
It's funny how companies have a stable DNA: Google comes from university research and continues to be good at research-y things, OTOH customer service...
Hi gemini, i’ve booked some tickets for théater. Please look into mail mailbox, schedule it in my calendar and confirm me the planning for next week.
Beeing able to use natural processing my mail and calendar make me switch to gemini (app), there’s no way to achieve that with chatgpt (app)
Gemini is now good enough, even if i prefer chatgpt.
I only care about what i can do in the app as paying customer, even if, aside from that, i am working in IT with the SDK openrouter & MCP intégration & whatever RAG & stuff for work
63 comments
[ 0.27 ms ] story [ 72.2 ms ] threadWasn't the consensus that 3.0 isn't that great compared to how it benchmarks? I don't even know anymore, I feel I'm going insane.
Ah, that explains the silly name for such an impressive tool. I guess it's more a more Googley name than what would have otherwise been chosen: Google Gemini Image Pro Red for Workspace.
Google, OpenAI, and Microsoft all have a very confusing product naming strategy where it’s all lumped under Gemini/ChatGPT/Copilot, and the individual product names are not memorable and really quite obscure. (What does Codex do again?)
Nano Banana doesn’t tell you what the product does, but you sure remember the name. It really rolls off the tongue, and it looks really catchy on social media.
Maybe on Benchmarks... but I'm forced to use Gemini at work everyday, while I use Opus 4.5 / GPT 5.2 privately every day... and Gemini is just lacking so much wit, creativity and multi-step problem solving skills compared to Opus.
Not to mention that Gemini CLI is a pain to use - after getting used to the smoothness of Claude Code.
Am I alone with this?
Everyone has to find what works for them and the switching cost and evaluation cost are very low.
I see a lot of comments generally with the same pattern “i cancelled my LEADER subscription and switched to COMPETITOR”… reminiscent of astroturf. However I scanned all the posters in this particular thread and the cancellers do seem like legit HN profiles.
Having said that, Google are killing it at the image editing right now. Makes me wonder if that’s because of some library of content and once Anthropocene acquires the same they’ll blow us away there too.
I am currently testing different IDEs including Antigravity, and I avoid that model at all cost. I will rather pay to use different model, than use Geminy 3.
It sucks at coding compared to OpenAI and Anthropic models and it is not clearly better as chat-bot (I like the context window). The images are best part of it as it is very steerable and fast.
But WTF? This was supposed to be the OpenAI killer model? Please.
If you hand an iPhone user an Android phone, they will complain that Android is awful and useless. The same is true vice versa.
This is in large part why we get so many conflicting reports of model behavior. As you become more and more familiar with a model, especially if it is in fact a good model, other good models will feel janky and broken.
There needs to be a greater distinction between models used for human chat, programming agents, and software-integration - where at least we benefitted from gemini flash models.
Most of my projects are on GPT at the moment, but we're nowhere too far gone that I can't move to others.
And considering just the general nonsense of Altman vs Musk, I might go to Gemini as a safe harbour (yes, I know how ridiculous that sounds).
So far, I've also noticed less ass-kissing by the Gemini robot ... a good thing.
Are you talking strictly about the respective command line tools as opposed to differences in the models they talk to?
If so, could you list the major pain points of Gemini CLI were Claude Code does better ?
It does need a solid test suite to keep it in check. But you can move very fast if you have well defined small tasks to give it. I have a PRD then breakdown epics, stories and finally the tasks with Pro first. Works very well.
Today, I asked Gemini 3 to find me a power supply with some spec; AC/DC +/- 15V/3A. It did a good job of spec extraction from the PDF datasheets I provided, including looking up how the device performance would degrade using a linear vs switch-mode PSU. But then it comes back with two models from Traco that don't exist, including broken URLs to Mouser. It did suggest running two Meanwell power supplies in series (valid), but 2/3 suggestions were BS. This sort of failure is particularly frustrating because it should be easy and the outputs are also very easy to test against.
Perhaps this is where you need a second agent to verify and report back, so a human doesn't waste the time?
Before this gpt nonsense they were such an aspiration for a better world. They quickly turned around, slayer core people from its structure and solely focus on capitalising that they seem to be stuck on dead waters.
I dont see any reasons to use gpt5 at all.
Just like the Disney movie, no touchy the Gemini.
Then there is the CLI; I always got "model is overloaded" errors even after trying weekly for a while. I found Google has this complex priority system; their bigger customers get priority (how much you spend determines queue prio).
Anybody did some serious work with gemini-cli? Is it at Opus level?
Terminal Bench supports my findings, GPT-5.2 and Opus 4.5 are consistently ahead. Only Junie CLI (Jetbrains exclusive) with Gemini 3 Flash scores somewhat close to the others.
It’s also why Ampcode made Gemini the default model and quickly back tracked when all of these issues came to light.
Antigravity was also painful to use at launch where more queries failed then succeeded, however they've basically solved that now to the point where it's become my most used editor/IDE where I've yet to hit a quota limit, despite only being on the $20/mo plan - even when using Gemini 3 Pro as the default model. I also can't recall seeing any failed service responses after a month of full-time usage. It's not the fastest model, but very happy with its high quality output.
I expected to upgrade to a Claude Code Max plan after leaving Augment Code, but given how good Antigravity is now for its low cost, I've switched to it as my primary full-time coding assistant.
Still paying for GitHub Copilot / Claude Pro for general VS Code and CC terminal usage, but definitely getting the most value of out my Gemini AI Pro sub.
Note this is only for development, docs and other work product. For API usage in products, I primarily lean on the cheaper OSS chinese models, primarily MiniMax 2.1 for tool calling or GLM 4.7/KimiK2/DeepSeek when extra intelligence is needed (at slower perf). Gemini Flash for analyzing Image, Audio & PDFs.
Also find Nano Banana/Pro (Gemini Flash Image) to consistently generate the highest quality images vs GPT 1.5/SDXL,HiDream,Flux,ZImage,Qwen, which apparently my Pro sub includes up to 1000/day for Nano Banana or 100/day for Pro?? [1], so it's hard to justify using anything else.
If Gemini 3 Pro was a bit faster and Flash a bit cheaper (API Usage), I could easily see myself switching to Gemini for everything. If future releases get smarter, faster whilst remaining aggressively priced, in the future - I expect I will.
[1] https://support.google.com/gemini/answer/16275805?hl=en
Google can afford to run Gemini for a looong time without any ads, while OpenAI needs necessarily to bring in some revenue: So OpenAI will have to do something (or they believe they can raise money infinitely)
Google can easily give Gemini without Ads to the users for the next 3 - 4 years, forcing OpenAI to cripple their product earlier with Ads because of the need for any revenue
I think Google & Antropic will be one of the two winners; not sure about OpenAI, Perplexity & Co - maybe OpenAI will somehow merge with Microsoft?
Beeing able to use natural processing my mail and calendar make me switch to gemini (app), there’s no way to achieve that with chatgpt (app)
Gemini is now good enough, even if i prefer chatgpt.
I only care about what i can do in the app as paying customer, even if, aside from that, i am working in IT with the SDK openrouter & MCP intégration & whatever RAG & stuff for work