@rubenssoto_ai Speed and cost are fine, what about the results/ outcomes?
Оригинал@rubenssoto_ai Speed and cost are fine, what about the results/ outcomes?
Оригинал@jshai0 GPT terra is not supposed to be close to these models in quality, but imagine this speed in computer usage
Оригинал@rubenssoto_ai Opus is next level
Оригинал@neerajjj6785 Opus is the best but if you need something fast, terra is the correct one
Оригинал@rubenssoto_ai It's better not to use terra lol
Оригинал@KrishnaBuildsAI hahaha I think you need to use Terra on the correct task
Оригинал@rubenssoto_ai what is terra doing😭
Оригинал@theaidesk_ Terra was trying to be fast hahahaa
Оригинал@rubenssoto_ai Terra is not much of an upgrade from Sol, but its cost is one for the books
Оригинал@knowixbuilds I think Terra is the correct model if you need something fast and cheap
Оригинал@rubenssoto_ai Did all three land the same result? 3 minutes next to 52 is the gap I'd want to diff before comparing the bills.
Оригинал@karanjagtiani04 You can check the result in the video
Оригинал@rubenssoto_ai just for me opus 5.5 is even better
Оригинал@yohakujpn You need to analyze which model is the best for each task...terra can be used for tasks you need something really fast
Оригинал@rubenssoto_ai really impressed with the speed and cost with tera here 👌
Оригинал@VanillaCache if you need something really fast, terra is the one
Оригинал@rubenssoto_ai $0.22 and 3m 25s versus $15.36 and 52m 36s is a massive difference. But the outputs aren't equivalent, which makes this a quality-adjusted cost question. Could you run all three against identical acceptance criteria? That's where Terra's economics get interesting.
Оригинал@YourAKShaw Could you guide me how to do that? I have never tested like this
Оригинал@rubenssoto_ai Opus took the scenic route
Оригинал@Eliopyr For sure, Opus quality is much better, Terra helps when you need something really fast
Оригинал@rubenssoto_ai nice test
Оригинал@rubenssoto_ai $15.36 vs $0.22 is a brutal gap for Opus
Оригинал@DanielZambrini and pretty fast right?
Оригинал@rubenssoto_ai quality isn't that good but good for quick conversations or small fixes
Оригинал@SahilPanhotra This model is pretty good at computer usage
Оригинал@rubenssoto_ai Opus wins for sure
Оригинал@rubenssoto_ai Opus is clearly the winner, but quite costly
Оригинал@LeoBuilds_ For sure mate, Terra has another goal, to be fast and cheap
ОригиналI dont really see how they can tout a faster smaller model as something valuable if every single use case is different for every single user. Like. ok its good and pressing buttons, but how many, how complex and how many times does it need to be fixed after. I dont get the cheap models.
Оригинал@BroadsideCode This model is supposed to be fast and cheap, so it's expected that it won't match the quality of Sol or Opus, especially in a single run. From what I've read, it's really good at computer use, and if you work through multiple iterations, you can get much better results.
Оригинал@rubenssoto_ai
Оригинал@rubenssoto_ai finally something nice
Оригинал@rubenssoto_ai Terra is not cheap, 30min on Terra would be ~$2.2. Sol 6.1 in this case is better.
Оригинал@pelolisu You should not calculate like this man, terra is much faster
Оригинал@rubenssoto_ai I'm doing some similar tests for creative arena - here is what I got so far
Оригинал@rubenssoto_ai Noo u can not say that! It’s better to join a complainers club and complain on every new model released before even testing it 😅
Оригинал@rubenssoto_ai Heyy, Haiku would’ve been very relevant to add in this test
Оригинал@Noah_Twenty It is a good model to compare, Im going to do that thanks
Оригинал@rubenssoto_ai Terra isnt the best but the cost difference IS INSANE
Оригинал@rubenssoto_ai Terra is fast but the result... not so much :D At least it was super quick. I think with a few iterations it could scratch the quality of the other two and still being faster
Оригинал@Ionkosm For sure man, quality opus is Unbitable, but the comparison was more to show the speed and cost.
Оригинал@rubenssoto_ai Terra at $0.22 and 3.5 minutes vs Opus 5.5 at $15.36 and 52 minutes is a huge gap. Did the outputs hold up in quality, or did Terra need more retries on the harder tasks?
Оригинал@Worldi123 One shot for all of them mate
Оригинал@rubenssoto_ai Opus crazy
Оригинал@AIVerseUday Opus is crazy good
Оригинал@rubenssoto_ai Same task, 70x cost gap. Magica routes work to the right model automatically, so your credits go on results and not on picking the wrong tool.
ОригиналLol, well Opus 5.5 is the leader as always. Its detail is strong. But I got the same result through http://multiai.store, it came out to $2.50 on Opus 5.5, but I feel like nobody's gonna beat that. But if Fable 5.5 comes out, then it'll be interesting to compare these two models
Оригинал@rubenssoto_ai Terra look Dope
Оригинал@rubenssoto_ai Looks like a roll of Nickles
Оригинал@rubenssoto_ai I like this)) You can feel the future in it.
Оригинал@GoooSAI For sure mate
Оригинал@rubenssoto_ai I would announce that ops5.5 win
Оригинал@Smart04261410 The quality for sure, but cost and speed terra is the winner
Оригинал@rubenssoto_ai Terra not much upgrade of Sol
Оригинал@rubenssoto_ai check this too https://x.com/Im_pritam18/status/2114879422146998310?s=20
Оригинал@rubenssoto_ai Terra for speed and volume, Opus for complex reasoning. Different tools for different jobs.
Оригинал