Video yükleniyor...
Video Yüklenemedi
GPT 6 Astra vs SWE 2.0 tested both models with same prompt at highest reasoning available > astra took 80 minutes to complete this task and costed $64 > swe 2.0 took 25 minutes and costed zero dollars really surprised by swe results here and astra looks nerfed right... show more
30,656 görüntüleme • 1 gün önce •via X (Twitter)
51 Yorum

you can play around here: both models were test in devin desktop app

I'd chosen SWE at first glance, but GPT-6 Astra did it better. Compare GPT-6 Astra to Nex-N2.5-Pro. It's currently free on OpenRouter.

lemme run same prompt on next will do tonight

Okay, please tag me when you do 🙏🏽

asrra 😭

it shows real human edited lmaoo

swe 2.0 did an incredible job

astra is a scam

How zero? Is it free to use?

yes via Devin

swe cooked here

this is insane

you guys cooked, cognition w

is swe 2.0 Kimi-k3.1 ?

you could say that but it's free

its soo good tho

I thought Astra was end game tf is going on

Astra is nerfed pretty hard rn

lol

wait $0 for this?😭 swe 2.0 won

free in devin for now

without a devin plan? (i was gifted a max btw)

yeah try on that without plan it's not available anywhere except Devin for now

how did free model cooked astra?

I wanna know too

Let's hope they can keep up the capacity and not having to nerf like others do

Oh wow. Swe 2.0 is absolutely incredible. Didn't expect this from a relatively small product/lab.

cognition is coming for top models

which model is SWE 2.0???

swe 2.0 is model name made by cognition available in Devin for free via their subs

oh not a fan of Devin, where does their sub start from

20 bucks

is swe 2.0 free in devin?

yeah free in devin that's why zero

Bro AI is becoming scary advanced

Damn u used 64$ for this output and swe 2.0 😱

yeah man, I have to test kek

Sure test but this type of test 🤣 🤣

This is insane bro

the way you put out output is diabolical dude

haha 😂😆

SWE 2.0 underrated

you should try it, it's free

costed isn't a word btw (at least not in this context) :P

if you can understand it's good, doesn't matter the wording, shows ai didn't write it kek

Astra don't have competition now

The $0 makes it hard to call this a fair comparison. Speed and cost gaps at highest reasoning usually mean different step counts, not a broken model. Output diff would tell you more than the timer.

There's no actual API conversion for SWE 2.0 hence $0? I get that it's free but there's no actual conversion if it were to be in api cost?

yeah i think so

How is the performance(speed and quality) compare to deepseek v4.1 flash?

80 minutes is brutal. Astra's reasoning depth is impressive but the token economics don't scale for production workflows. Have you tested it with smaller, decomposed prompts? Often cuts time by 60% without quality loss.
