Gemini 2.0 Pro & Flash Lite : This is THE BEST GEMINI MODEL YET but DOES IT BEAT DEEPSEEK-R1?

Поділитися
Вставка
  • Опубліковано 6 лют 2025

КОМЕНТАРІ • 74

  • @hamza-325
    @hamza-325 17 годин тому +16

    10:32 Gemini 2 pro just designed the best SVG butterfly so far! No other model was even close to this!

  • @rahuldinesh2840
    @rahuldinesh2840 22 години тому +41

    I used Gemini 2.0 and it solved a code that Claude 3.5 sonnet wasn’t able to. I thought it did it accidentally.

    • @micbab-vg2mu
      @micbab-vg2mu 21 годину тому +7

      the same Gemini 2.0 is not better than Claude 3.5

    • @memeherp166
      @memeherp166 20 годин тому

      same never expected anything from gemini, even qwen 2.5 max seems better

    • @mrkoalamanda
      @mrkoalamanda 19 годин тому

      But Agentic capability are same bad as R1,V3

    • @rahuldinesh2840
      @rahuldinesh2840 16 годин тому

      @@mrkoalamanda Anyway if it involves just one LLM and API's then the task can be accomplished by codes and wouldn't need agents.

  • @gemini_537
    @gemini_537 Годину тому

    Gemini 2.0 Flash Thinking with Search is my favorite! It automatically determines if a search if needed before answering.

  • @BeyondReality522
    @BeyondReality522 17 годин тому +6

    I think in terms of performance Gemini lost to R1, but the 1M context window is enough to make an app in one chat

  • @InAMinute-ws3yv
    @InAMinute-ws3yv 16 годин тому +2

    You are the best channel, who says what audiences wants to listen, no bullshitting and straight to point. Keep up the good job. ❤

  • @nathanflossome3297
    @nathanflossome3297 22 години тому +14

    the context window makes up for it 1m token is more than anyone

    • @cbgaming08
      @cbgaming08 22 години тому +3

      It is 2 million, sir.

    • @fabiankliebhan
      @fabiankliebhan 21 годину тому +2

      @@cbgaming08 For pro it is 2 Million, for flash 1 Million

    • @cbgaming08
      @cbgaming08 21 годину тому +1

      @@fabiankliebhan yezzir!

  • @varunaeeriyaulla
    @varunaeeriyaulla 19 годин тому +4

    Deepseek is unusable for a week. I tried both Flash 2.0 and pro. Looks good for my use case.

  • @RM-xs3ci
    @RM-xs3ci 17 годин тому +4

    I wish there were UI benchmarks. I use it a TON for UI development because I am so bad at design

  • @curiousgeorge7515
    @curiousgeorge7515 19 годин тому +2

    I just tried Gemini 2.0 Thinking experimental. It was absolutely horrible for my use case! I am the record holder for the fastest assembly routines for 6502 arithmetic, and I tried to prompt it towards the optimal solution, but it just doesn't understand. It had no concept that this CPU can only operate on 8 bit values. It tried to load the high byte of a 32 bit number into a register, then the low byte, thus missing the middle two bytes. It also doesn't understand the concept of self-modifying code, even when given an example. Claude and Deepseek are the only models which produced sensible results in my case. Claude even used fragments of my world record post online in it's commentary; obviously my code was in it's data set.

  • @TheReferrer72
    @TheReferrer72 21 годину тому +5

    Oh those Butterfly's are nice, must be the image generation training data part of these models doing its thing!

  • @hamloji
    @hamloji 21 годину тому +8

    Gemini 2.0 Pro is very bad at coding and makes tons of silly mistakes.

    • @MonetizeAIAgents
      @MonetizeAIAgents 13 годин тому +1

      Yeah and also works super bad with n8n ai agents

    • @elbrody252
      @elbrody252 7 годин тому +1

      what cheap ia to use for code then?

    • @MarvijoSoftware
      @MarvijoSoftware 2 години тому

      R1 with a provider like Hyperbolic is working for me. DeepSeek V3 also works well with providers like OpenRouter. Then use Sonnet if any of them are stuck, because it's expensive ​@@elbrody252

    • @BobbyDenniegetlost
      @BobbyDenniegetlost 2 години тому

      All google things are hype kn UA-cam but fall bad when test it in real life lol, practical to own the platform 😂

  • @kevinp1514
    @kevinp1514 22 години тому +6

    Just check Question 4, and you’ll know directly if LLMs are a beast or not ...

  • @joeseabreeze
    @joeseabreeze 5 годин тому

    I was looking through your videos to find that tool that you demonstrated a while ago that allows you to point to several models and compare their outputs. What's the name of the tool?

  • @cmptrtube
    @cmptrtube 17 годин тому +1

    Yeah the leader of Gemini AI guy said that he wasn't as impressed over the performance boost, but he probably means just the 2.0 flash because it been a while ago.

  • @aryindra2931
    @aryindra2931 21 годину тому +2

    Deepseek-r1 is king for LLM model for now😂😂

  • @HoRNET_FPV
    @HoRNET_FPV 19 годин тому +1

    GEMINI is my go to for a while with RooCode, it much better than R1, like by miles

  • @Nullzero98
    @Nullzero98 21 годину тому +2

    Is this model a thinking model? Pretty crazy that deepseek is still on top.

    • @IamBlue.
      @IamBlue. 17 годин тому +2

      No. The pro think model is not out yet I believe

  • @smissu1
    @smissu1 5 годин тому

    I think the only benefit of using these models are for their multi-model capabilities. At least google had the good sense to make the models cheap considering they are not as good as V3 or R1. Gemini version 2.5 or 3 should be as good or better than DS V3/R1 or don't even put out another model. Now, there is no excuse why Google would produce a closed source product that would not perform as good as DS models. Just figure out how to increase the context size, add multi model capabilities, train the model using DS process and Google would have a product worth paying for IMO. Lastly, google could probably train a DS/MOE type model a lot faster given the fact google has access to Nvidia's latest and greatest processors.

  • @chadpogs7973
    @chadpogs7973 22 години тому +1

    Wow another video ❤

  • @allslav_ru
    @allslav_ru 22 години тому +3

    Is it better than Gemini Exp 1206? It seems to me that this is the same model, just renamed.

  • @SudeeptoDutta
    @SudeeptoDutta 19 годин тому +1

    I'm currently using Gemini 2.0 Flash Experimental using API key in my VSCODE Continue extension. What should I change to point to the stable Gemini 2.0 Flash model ?

  • @holdthetruthhostage
    @holdthetruthhostage 8 годин тому

    2 Million Token Window, Man Anthropic just doing Nothing man

  • @Dutep
    @Dutep 5 годин тому

    Do you guys think that it's now the best model to use in free Copilot in VS Code?

  • @IunahYT
    @IunahYT 19 годин тому +1

    it's good but how do they achieve 1 million tokens context, is it a sliding context window?

    • @IamBlue.
      @IamBlue. 17 годин тому

      No, I think its full context Window.

  • @thiagofelizola
    @thiagofelizola 10 годин тому

    Love your videos.
    Please compare low costs models for api devs for text generation.
    gpt 4o-mini vs gemini 2.0 flash vs gemini 2.0 flash lite

    • @MarvijoSoftware
      @MarvijoSoftware 2 години тому +1

      Between the ones you mentioned it's definitely Gemini 2 Flash

    • @thiagofelizola
      @thiagofelizola 2 години тому

      @@MarvijoSoftware Thank you

  • @rtkoyt
    @rtkoyt 14 годин тому +1

    😶‍🌫️😶‍🌫️😶‍🌫️😶‍🌫️

  • @rbnmbn2
    @rbnmbn2 20 годин тому

    How do you churn out videos at this rate? I can barely keep up😅

  • @rousabout7578
    @rousabout7578 21 годину тому

    This model can deepthink with a prompt in system instruction. Still fixates on hallucinations, but imho not as bad as previous models from google. Strong nudging can help, but it blames user when it finally acknowledges its error.

  • @oskarmariagrande1855
    @oskarmariagrande1855 16 годин тому

    ye true AICodeKing; is *insanely better*; brightening our days; transcending his cohort; always bringing forth the freshest produce and impeccable delivery

  • @AnuragRai-xy7kh
    @AnuragRai-xy7kh 22 години тому +7

    You point about deepseek The api is down for straight 7 days and the chat interface also does not respond in deep think mode the how can we compare it with others if not work at all.

    • @AICodeKing
      @AICodeKing  22 години тому +8

      It's an opensource model. There are a bunch of providers who have it as well including Together, Hyperbolic and a bunch of others.

    • @AnuragRai-xy7kh
      @AnuragRai-xy7kh 22 години тому +1

      @AICodeKing they cost more than the deepseek

    • @neazybanga
      @neazybanga 21 годину тому +3

      @@AnuragRai-xy7kh you have the option to run it locally

    • @AnuragRai-xy7kh
      @AnuragRai-xy7kh 21 годину тому

      @neazybanga yeh but it won't be that effective as 600B model I know open source and all but it should be reliable as well

    • @kozydot
      @kozydot 21 годину тому

      nVidia NIM offers free 1000 credits and it has R1

  • @dunai2012
    @dunai2012 18 годин тому

    But how come its stock plummeted this morning?

    • @smissu1
      @smissu1 5 годин тому

      Revenue is down a bit. Probably bc people are starting to use google search less as there are better AI assisted search alternatives.

  • @IMZEMPYY
    @IMZEMPYY 13 годин тому

    hey bro, from somalia

  • @innerzenn
    @innerzenn 15 годин тому

    just found out i can switch between different audio languages on youtube

  • @andygray9429
    @andygray9429 20 годин тому +1

    Both of those synth keyboards the tuning sounded wrong

  • @michaelcdoty
    @michaelcdoty 15 годин тому

    Alright, meta's turn.

  • @brianrowe1152
    @brianrowe1152 18 годин тому

    Thank you

  • @Ahmed_Elghazaly
    @Ahmed_Elghazaly 21 годину тому

    Try using it with sonnet 3.5 system prompt

  • @Cine95
    @Cine95 20 годин тому

    well its not even that good though there thinking model is kinda cracked

  • @jackflash6377
    @jackflash6377 19 годин тому +3

    google = too much DEI

  • @eduardomoura2813
    @eduardomoura2813 17 годин тому

    hard to justify any other ai when deepseek is around.

    • @MarvijoSoftware
      @MarvijoSoftware 2 години тому

      Agreed. Even o3-mini doesn't compete when I tested

  • @michaelm5480
    @michaelm5480 11 годин тому

    Add to new test to make android app

  • @userj-s2000
    @userj-s2000 18 годин тому

    2.0 better than sonnet atm

    • @MarvijoSoftware
      @MarvijoSoftware 2 години тому

      I beg to differ. How did you test them?

  • @Hizunori
    @Hizunori 22 години тому

    🤑