@PawelHuryn claude sonnet better than opus?
الأصللذا اختبرت GPT-6.1 Sol في عمل حقيقي: مستودعان (repos)، 105 أخطاء مزروعة. ابحث وأصلح ما يمكنك. على عكس GPT-6 Sol، الذي كان مجرد GPT-5.6 Terra معطوب القوة، هذا النموذج حقيقي. النتائج: - GPT-6 Astra (الحد الأقصى): 45 مقابل 33 دولارًا - GPT-6.1 Sol (الحد الأقصى): 44 مقابل 6.56 دولارًا - GPT-5.6 Sol (الحد الأقصى): 43.5 مقابل 95.35 دولارًا - Opus 5.5 (الحد الأقصى): 41.7 مقابل 58.53 دولارًا - GPT-6 Sol (الحد الأقصى): 29.3 مقابل 9.33 دولارًا مع نموذج كهذا، لا أهمية لخصم 50% على خطة الـ 200 دولار. n=1. المزيد من عمليات التشغيل والنتائج بمستويات جهد مختلفة ستنزل في هذه السلسلة ove
0
0
0
0
التعليقات 42
-
-
@PawelHuryn Sonnet 5.5 in first, what?
الأصل -
@PawelHuryn @grok explain
الأصل -
@PawelHuryn GPT 6.1 sol has been absolutely stupid for me. https://x.com/cyberpeterg/status/2105313537543303596?s=20
الأصل -
@PawelHuryn what was the 1 bug Astra caught that Sol missed?
الأصل -
@PawelHuryn Nuts
الأصل -
@PawelHuryn 44 bugs, $6.56. Cost-per-fix is the ladder.
الأصل -
@PawelHuryn WOWIE! amazing results :)
الأصل -
@PawelHuryn @grok sol 6.1 is clearly cutting into OAI's margins. Is this "race to the bottom" reminiscent of early 2000's internet prices? When did this race start? When did it end? Outcomes?
الأصل -
@PawelHuryn Просто на подписке за 200$ можно было бы бесконечно пользоваться 6.1 sol ultra и не покупать кредиты, openai это непонравилось😂
الأصل -
@PawelHuryn do the fixes get checked for new bugs too, or just whether the planted ones are gone?
الأصل -
@PawelHuryn Opus 5.5 at 41.7 for $58.53 against 6.1 Sol at 44 for $6.56 is the line that matters here. Once you log a few more runs, I'd love to see whether the misses overlap or whether Opus catches bugs Sol never touches, because that decides routing versus just picking one.
الأصل -
@PawelHuryn how much you got from openai? "With a model like this, the 50% cut to the $200 plan doesn't matter." all these are just for this sentences to plant the idea it's ok. it's not ok bro.
الأصل -
@PawelHuryn Short: 6.1 Sol finally sits on the right shelf. Not the bug king. The king of cost per bug found.
الأصل -
@PawelHuryn Interesting
الأصل -
@PawelHuryn There is alternative 3D visualization of the results, can make 3 axis comparison easier. https://icauro.com/toabundance?benchmark=bug-hunt
الأصل -
@PawelHuryn The only problem? "remove the xx button from the page" ... 'valutating bla bla bla' ..... 10 minutes later 'button removed, i'll now verify if the button is not visible' ..... . 15 minutes... 'the button is removed and not present on the page' (but still in temp page) 30m tot
الأصل -
@PawelHuryn thanks for running this and sharing the test results!
الأصل -
@PawelHuryn A bit useless to show the highest level of AI. The real challenge comes when you test on medium.
الأصل -
@PawelHuryn is it just me or is gpt 6.1 sol slow? what tps are you getting?
الأصل -
@PawelHuryn In terms of criticality (identifying more impactful bugs), was GPT-6.1 Sol on par with GPT-6 Astra and Fable 5.1? Btw, thanks for this, this is gold! 🤝
الأصل -
@PawelHuryn https://x.com/SlovenskiGlas1/status/2105265982948180341
الأصل -
@PawelHuryn GPT 6.1 Sol is basically a telenovela: the cast is great, young, and gorgeous, the costumes are stunning, but almost nothing actually happens. You could easily skip four episodes and still not miss a beat.
الأصل -
@PawelHuryn TY
الأصل -
@PawelHuryn Glad you're adding n=3. I'd put a bug-by-bug stability view next to the totals: fixing 44 different bugs each run creates a different review workload from reliably fixing the same 44.
الأصل-
@jakestone2306 It's not 100% deterministic. Bugs differ a lot between runs. This view: https://bughunt.productcompass.pm/?preset=featured&view=coverage
الأصل-
@PawelHuryn @jakestone2306 GPT-5.6 Sol + GPT-6.1 Sol looks like an interesting combination or is it just a coincidence that one finds bugs at the end the other one missed ?
الأصل-
@PawelHuryn @jakestone2306 Uh, just saw that GPT-5.6 Sol is horrible expensive, I would get away cheaper with Astra ! ... but combination of multiple models might be a cost effective approach to try.
الأصل-
@SvenMeyer It could be complementary coverage, or just run-to-run variation. I'd compare two passes of one model with one pass each of two models, at the same total budget. Count newly fixed bugs on the second pass, not just the combined score.
الأصل
-
-
-
-
-
@PawelHuryn For finding bugs, does it make sense to first run Sol 6.1. Then run Opus 5.5 with the knowledge of known bugs from Sol. Can it lower the total cost while catching more bugs?
الأصل -
@PawelHuryn i used 6.1 for bug findings. it was much better than opus 5.5. but opus is much better in performance, design and smart code
الأصل -
@PawelHuryn 跟我在實際工作中使用6.1 sol xhigh 的體感一樣，有好又省！好像有點慢？
الأصل -
@PawelHuryn I would advise against testing every model on Max reasoning. Most tend perform better on Medium or High, like my test here where Terra and Luna both suffer on Max:
الأصل -
@PawelHuryn The real story is the price ratio, not the score — 44 bugs for $6.56 vs 45 for $33. At one-fifth the cost you can just run five passes and brute-force the gap. Makes the whole "Astra got shelved for safety" line look more like a pricing problem.
الأصل -
@PawelHuryn 6.1 sol’s performance for the price is honestly wild.
الأصل -
@PawelHuryn Great overview! Are you planning to also check gpt-6.1-luna?
الأصل -
@PawelHuryn it matters. this model ships far more slop than 6 sol did
الأصل -
@PawelHuryn Would be nice to see amount of slop and regressions introduced. Gemini for me was terrible for fixing things, it wasn't using good architecture, patterns and introduced a lot of regression. But the results may actually vary by how good your agentic context is in the workspace.
الأصل
스크롤하면 더 불러옵니다