Iam_

@SPAC89 • 3,452 subscribers

Really excited about AGI, learning more every day about LLMs and the future of technology, and sharing my own thoughts along the way

Shorts

🔥Gemini 4 Hydrogen is FINALLY coming to the $20 Pro plan and will be available to everyone in less than 7 hours! it was just spotted on Google Cloud, with pricing at $0.75 input, $3.75 output and $0.0375 cache. This is going to be a really fast model, like Flash but with frontier level performance if OpenAI doesn't release the GPT 6.2 family soon, they're cooked

🔥Gemini 4 Hydrogen is FINALLY coming to the $20 Pro plan and will be available to everyone in less than 7 hours! it was just spotted on Google Cloud, with pricing at $0.75 input, $3.75 output and $0.0375 cache. This is going to be a really fast model, like Flash but with frontier level performance if OpenAI doesn't release the GPT 6.2 family soon, they're cooked

17,381 просмотров

GPT 6.1 Sol Ultra vs DeepSeek V4.1 Flash 1017 Max, I still can't believe a model that's 90% cheaper can produce results this good, how is this even possible? Both models took roughly the same amount of time since most of it was spent rendering, but the quality DeepSeek managed to achieve is incredible, especially considering the API cost was just 0.44 cents for the entire test! I think having access to free web search is making a huge difference and giving DeepSeek a much bigger advantage than before, especially with its native multimodal capabilities. The more I test this model, the more I wonder how they're managing to offer so much at such a low price, I'm still running even bigger tests with different models to see how far it can go, more results coming soon!

GPT 6.1 Sol Ultra vs DeepSeek V4.1 Flash 1017 Max, I still can't believe a model that's 90% cheaper can produce results this good, how is this even possible? Both models took roughly the same amount of time since most of it was spent rendering, but the quality DeepSeek managed to achieve is incredible, especially considering the API cost was just 0.44 cents for the entire test! I think having access to free web search is making a huge difference and giving DeepSeek a much bigger advantage than before, especially with its native multimodal capabilities. The more I test this model, the more I wonder how they're managing to offer so much at such a low price, I'm still running even bigger tests with different models to see how far it can go, more results coming soon!

194,012 просмотров

🚨 Gemini 4 Carbon vs Kimi K3.1, after my first tests I feel like both models could easily compete with Opus 5.5 Medium when it comes to 3D, and I'm really liking what I'm seeing from both of them! The quality is impressive and they're both very fast, but I think Kimi K3.1 is going to surprise a lot of people, myself included. If they manage to release it at prices similar to DeepSeek, it could be game over for a lot of closed source coding models from US labs, especially when you consider how good the quality already looks in these early tests. Now I'm just hoping they finally release the model along with its open weights so we can run a quantized version locally! I can't wait to see how it performs outside Arena and how much we can push it with more demanding projects. What a great week we have ahead of us!

🚨 Gemini 4 Carbon vs Kimi K3.1, after my first tests I feel like both models could easily compete with Opus 5.5 Medium when it comes to 3D, and I'm really liking what I'm seeing from both of them! The quality is impressive and they're both very fast, but I think Kimi K3.1 is going to surprise a lot of people, myself included. If they manage to release it at prices similar to DeepSeek, it could be game over for a lot of closed source coding models from US labs, especially when you consider how good the quality already looks in these early tests. Now I'm just hoping they finally release the model along with its open weights so we can run a quantized version locally! I can't wait to see how it performs outside Arena and how much we can push it with more demanding projects. What a great week we have ahead of us!

40,364 просмотров

🚨 Fable 5.5 XHigh vs GPT 6.1 Sol Ultra Fable 5.5 now seems to be routing through both the web app and Claude Code for most of us, On my Claude Pro x5 plan, this test used around 7% of my weekly limit without any agents, Running the same kind of test on Codex x20 used only about 1% of my weekly limit Quality wise, both were really strong. In terms of speed, they were also pretty close, with both taking roughly 30 minutes to finish, I’m running a lot more tests in parallel right now to see whether there’s actually a meaningful difference between them once you push both models harder

🚨 Fable 5.5 XHigh vs GPT 6.1 Sol Ultra Fable 5.5 now seems to be routing through both the web app and Claude Code for most of us, On my Claude Pro x5 plan, this test used around 7% of my weekly limit without any agents, Running the same kind of test on Codex x20 used only about 1% of my weekly limit Quality wise, both were really strong. In terms of speed, they were also pretty close, with both taking roughly 30 minutes to finish, I’m running a lot more tests in parallel right now to see whether there’s actually a meaningful difference between them once you push both models harder

72,108 просмотров

🔴 GLM-5.5 could be just a few days away! Statistically, Zhipu has been releasing new models every 61 days on average this year GLM-4.7 → GLM-5: 51 days GLM-5 → GLM-5.1: 55 days GLM-5.1 → GLM-5.2: 70 days GLM-5.2 → GLM-5.3: 59 days Avg: 61 days Now: 76 days since GLM-5.3 Next GLM-5.5 est. ~Nov 3 (80%: Oct 30 – Nov 12)

🔴 GLM-5.5 could be just a few days away! Statistically, Zhipu has been releasing new models every 61 days on average this year GLM-4.7 → GLM-5: 51 days GLM-5 → GLM-5.1: 55 days GLM-5.1 → GLM-5.2: 70 days GLM-5.2 → GLM-5.3: 59 days Avg: 61 days Now: 76 days since GLM-5.3 Next GLM-5.5 est. ~Nov 3 (80%: Oct 30 – Nov 12)

14,430 просмотров

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

40,874 просмотров

I just tried the new Gemini-4 Pro Preview and honestly, for 3D work it’s right up there with Fable 5.1 and GPT-6 Astra, all in a single shot, I genuinely didn’t expect it to be this good, It only used around 10% of my weekly limit on the $20 plan, I’m going to make a comparison video against Opus 5.2 or Fable and Astra if I can, I still can’t believe it, From what I’ve tested so far, this is easily top 1 or 2 for the best one shot execution I’ve seen

I just tried the new Gemini-4 Pro Preview and honestly, for 3D work it’s right up there with Fable 5.1 and GPT-6 Astra, all in a single shot, I genuinely didn’t expect it to be this good, It only used around 10% of my weekly limit on the $20 plan, I’m going to make a comparison video against Opus 5.2 or Fable and Astra if I can, I still can’t believe it, From what I’ve tested so far, this is easily top 1 or 2 for the best one shot execution I’ve seen

27,952 просмотров

Xiaomi MiMo-V2.6 Pro vs MiMo-V2.6 Flash, Honestly, I didn’t expect them to be this cheap, The whole test cost me just a few cents and took around an hour From what I’m seeing in my benchmarks, MiMo V2.6 Pro is even doing a bit better than GLM 5.3 in some areas, But the thing that surprised me the most is the efficiency, For the price, this is kinda crazy, Xiaomi is really cooking with these models

Xiaomi MiMo-V2.6 Pro vs MiMo-V2.6 Flash, Honestly, I didn’t expect them to be this cheap, The whole test cost me just a few cents and took around an hour From what I’m seeing in my benchmarks, MiMo V2.6 Pro is even doing a bit better than GLM 5.3 in some areas, But the thing that surprised me the most is the efficiency, For the price, this is kinda crazy, Xiaomi is really cooking with these models

18,129 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

🔥Gemini 4 Hydrogen is FINALLY coming to the $20 Pro plan and will be available to everyone in less than 7 hours! it was just spotted on Google Cloud, with pricing at $0.75 input, $3.75 output and $0.0375 cache. This is going to be a really fast model, like Flash but with frontier level performance if OpenAI doesn't release the GPT 6.2 family soon, they're cooked

🔥Gemini 4 Hydrogen is FINALLY coming to the $20 Pro plan and will be available to everyone in less than 7 hours! it was just spotted on Google Cloud, with pricing at $0.75 input, $3.75 output and $0.0375 cache. This is going to be a really fast model, like Flash but with frontier level performance if OpenAI doesn't release the GPT 6.2 family soon, they're cooked

17,381 просмотров • 22 часов назад

GPT 6.1 Sol Ultra vs DeepSeek V4.1 Flash 1017 Max, I still can't believe a model that's 90% cheaper can produce results this good, how is this even possible? Both models took roughly the same amount of time since most of it was spent rendering, but the quality DeepSeek managed to achieve is incredible, especially considering the API cost was just 0.44 cents for the entire test! I think having access to free web search is making a huge difference and giving DeepSeek a much bigger advantage than before, especially with its native multimodal capabilities. The more I test this model, the more I wonder how they're managing to offer so much at such a low price, I'm still running even bigger tests with different models to see how far it can go, more results coming soon!

GPT 6.1 Sol Ultra vs DeepSeek V4.1 Flash 1017 Max, I still can't believe a model that's 90% cheaper can produce results this good, how is this even possible? Both models took roughly the same amount of time since most of it was spent rendering, but the quality DeepSeek managed to achieve is incredible, especially considering the API cost was just 0.44 cents for the entire test! I think having access to free web search is making a huge difference and giving DeepSeek a much bigger advantage than before, especially with its native multimodal capabilities. The more I test this model, the more I wonder how they're managing to offer so much at such a low price, I'm still running even bigger tests with different models to see how far it can go, more results coming soon!

194,012 просмотров • 26 дней назад

Qwen 4 is free right now through Qoduck Qoder! It's pretty slow due to the crazy demand, but not bad at all for a 27GB model. I've got several benchmarks running in parallel, Give it a try for free and see for yourself, I think you'll be surprised! 👀

Qwen 4 is free right now through Qoduck Qoder! It's pretty slow due to the crazy demand, but not bad at all for a 27GB model. I've got several benchmarks running in parallel, Give it a try for free and see for yourself, I think you'll be surprised! 👀

27,263 просмотров • 5 дней назад

ChatGPT just got its biggest update of 2026! GPT-6 Pro can now launch subagents to handle research tasks in parallel without using up your Codex quota, allowing it to delegate different parts of a project and finish the research much faster, This update really feels like a whole new experience, and what I love most is that it automatically creates a plan for each task you delegate and keeps you updated on what's been completed and how the entire project is progressing, The $100 Pro plan gives you 50 messages per week in Pro mode, while the $200 plan comes with 100 messages per week, I'm having so much fun with this update, it's a huge improvement!

ChatGPT just got its biggest update of 2026! GPT-6 Pro can now launch subagents to handle research tasks in parallel without using up your Codex quota, allowing it to delegate different parts of a project and finish the research much faster, This update really feels like a whole new experience, and what I love most is that it automatically creates a plan for each task you delegate and keeps you updated on what's been completed and how the entire project is progressing, The $100 Pro plan gives you 50 messages per week in Pro mode, while the $200 plan comes with 100 messages per week, I'm having so much fun with this update, it's a huge improvement!

99,446 просмотров • 27 дней назад

GPT-6.1 Sol ULTRA ran for 25 minutes and only used 1% of my weekly quota, It’s seriously fast and powerful, almost like Astra, but much cheaper to run, For me, this is the kind of model you can actually use 24/7 without constantly worrying about limits, From now on, it’s probably going to be my default model, Honestly, out of everything announced at DevDay, this might be my favorite update. In my experience, it feels like the most efficient model OpenAI has released so far

GPT-6.1 Sol ULTRA ran for 25 minutes and only used 1% of my weekly quota, It’s seriously fast and powerful, almost like Astra, but much cheaper to run, For me, this is the kind of model you can actually use 24/7 without constantly worrying about limits, From now on, it’s probably going to be my default model, Honestly, out of everything announced at DevDay, this might be my favorite update. In my experience, it feels like the most efficient model OpenAI has released so far

142,184 просмотров • 1 месяц назад

DeepSeek V4.1 Flash 1017 is hitting 244 tokens per second, that's incredible! It's even faster than GPT 6.1 Sol in Ultrafast mode while offering intelligence comparable to GPT 5.6 Sol, what a time to be following AI! I still can't understand how they can offer this level of quality and speed at such a low price, and from my first tests I've seen speeds reaching almost 300 tokens per second. It now has its own built in web research capabilities and is completely free to use through DeepSeek's official harness until October 31, The improvements in both coding and 3D are also really noticeable compared to previous versions, and after everything I've tested so far, I have no doubt this is a frontier level model, I still can't believe how quickly DeepSeek is improving!

DeepSeek V4.1 Flash 1017 is hitting 244 tokens per second, that's incredible! It's even faster than GPT 6.1 Sol in Ultrafast mode while offering intelligence comparable to GPT 5.6 Sol, what a time to be following AI! I still can't understand how they can offer this level of quality and speed at such a low price, and from my first tests I've seen speeds reaching almost 300 tokens per second. It now has its own built in web research capabilities and is completely free to use through DeepSeek's official harness until October 31, The improvements in both coding and 3D are also really noticeable compared to previous versions, and after everything I've tested so far, I have no doubt this is a frontier level model, I still can't believe how quickly DeepSeek is improving!

83,090 просмотров • 26 дней назад

Gemini 4 Argon High vs Muse Wonder Full 🍉, the crazy thing is that Muse Wonder wasn't even trained specifically for 3D, yet it still beats Gemini 4 in most of my tests, with both costing about the same per task, In this article I share a much deeper look at my tests and how Wonder compares with other frontier models like Opus 5.5, GPT-6 Astra and more, A little spoiler, Wonder Full Max and Xhigh are really good, they're definitely expensive but well worth trying!

Gemini 4 Argon High vs Muse Wonder Full 🍉, the crazy thing is that Muse Wonder wasn't even trained specifically for 3D, yet it still beats Gemini 4 in most of my tests, with both costing about the same per task, In this article I share a much deeper look at my tests and how Wonder compares with other frontier models like Opus 5.5, GPT-6 Astra and more, A little spoiler, Wonder Full Max and Xhigh are really good, they're definitely expensive but well worth trying!

81,925 просмотров • 29 дней назад

🤯 Qwen 4 27B was on Arena last week under the name Kalmia and honestly, for a 27B model it's ridiculously good I can't wait to get my hands on the full release. I genuinely think it's going to exceed a lot of people's expectations Qwen 3.8 27B is already insanely good, so I can only imagine what's coming next. I'm honestly speechless

🤯 Qwen 4 27B was on Arena last week under the name Kalmia and honestly, for a 27B model it's ridiculously good I can't wait to get my hands on the full release. I genuinely think it's going to exceed a lot of people's expectations Qwen 3.8 27B is already insanely good, so I can only imagine what's coming next. I'm honestly speechless

17,568 просмотров • 6 дней назад

Muse Wonder Full Max might actually be the best AI model in the world right now! I'm running it through Muse CLI with the $50 Muse Code Power Usage plan, and I'm genuinely impressed. It's incredibly fast, performs really well, and the usage limits are surprisingly generous. So far, it's doing an amazing job! I'm currently testing it head to head against Opus 5.5 Max and GPT-6 Astra Ultra, and I actually think Muse Wonder is doing a much better job I'll be sharing the full results soon, including total costs, completion times, and overall performance Huge credit to Meta for making such a powerful, affordable, and fast model accessible to so many people around the world, Amazing work!

Muse Wonder Full Max might actually be the best AI model in the world right now! I'm running it through Muse CLI with the $50 Muse Code Power Usage plan, and I'm genuinely impressed. It's incredibly fast, performs really well, and the usage limits are surprisingly generous. So far, it's doing an amazing job! I'm currently testing it head to head against Opus 5.5 Max and GPT-6 Astra Ultra, and I actually think Muse Wonder is doing a much better job I'll be sharing the full results soon, including total costs, completion times, and overall performance Huge credit to Meta for making such a powerful, affordable, and fast model accessible to so many people around the world, Amazing work!

71,332 просмотров • 1 месяц назад

Muse Spark 1.3 Ultra Contributor vs Fable 5.1 xHigh Same prompt, both ran for roughly 2 hours The prompt had a self improvement rule: if the independent judges scored the result below 9.5/10, it had to keep improving and try again, What shocked me most was that Muse Spark just NEVER stopped, It went through 20 self improvement loops, launching 3 agents each time basically 60+ agent runs over 2 hours And the cost?, Less than $1, Yes, under $1… in Ultra mode ,This completely exceeded my expectations Huge credit to Meta, this thing is a work of art

Muse Spark 1.3 Ultra Contributor vs Fable 5.1 xHigh Same prompt, both ran for roughly 2 hours The prompt had a self improvement rule: if the independent judges scored the result below 9.5/10, it had to keep improving and try again, What shocked me most was that Muse Spark just NEVER stopped, It went through 20 self improvement loops, launching 3 agents each time basically 60+ agent runs over 2 hours And the cost?, Less than $1, Yes, under $1… in Ultra mode ,This completely exceeded my expectations Huge credit to Meta, this thing is a work of art

150,400 просмотров • 2 месяцев назад

GPT-6.1 Terra Ultra in Codex is the fastest GPT model I've ever used, and that's without even enabling Fast mode! I still can't believe what I just saw, it completed this benchmark in less than 3 minutes when the same kind of task normally takes over 30 minutes. I wasn't expecting this level of speed at all, and now I'm really curious to see how far OpenAI can push its inference optimizations. If they manage to bring this kind of performance to GPT-6.2 Astra, I think they could seriously compete with Fable 5.5, especially because when two models are already incredibly capable, speed can make all the difference in real world projects. I'm already asking Codex to make GPT-6.1 Terra High the default model for all my automations, I really want to see what happens when I start running my workflows with this kind of speed!

GPT-6.1 Terra Ultra in Codex is the fastest GPT model I've ever used, and that's without even enabling Fast mode! I still can't believe what I just saw, it completed this benchmark in less than 3 minutes when the same kind of task normally takes over 30 minutes. I wasn't expecting this level of speed at all, and now I'm really curious to see how far OpenAI can push its inference optimizations. If they manage to bring this kind of performance to GPT-6.2 Astra, I think they could seriously compete with Fable 5.5, especially because when two models are already incredibly capable, speed can make all the difference in real world projects. I'm already asking Codex to make GPT-6.1 Terra High the default model for all my automations, I really want to see what happens when I start running my workflows with this kind of speed!

39,105 просмотров • 17 дней назад

🚨 Fable 5.5 XHigh vs GPT 6.1 Sol Ultra Fable 5.5 now seems to be routing through both the web app and Claude Code for most of us, On my Claude Pro x5 plan, this test used around 7% of my weekly limit without any agents, Running the same kind of test on Codex x20 used only about 1% of my weekly limit Quality wise, both were really strong. In terms of speed, they were also pretty close, with both taking roughly 30 minutes to finish, I’m running a lot more tests in parallel right now to see whether there’s actually a meaningful difference between them once you push both models harder

🚨 Fable 5.5 XHigh vs GPT 6.1 Sol Ultra Fable 5.5 now seems to be routing through both the web app and Claude Code for most of us, On my Claude Pro x5 plan, this test used around 7% of my weekly limit without any agents, Running the same kind of test on Codex x20 used only about 1% of my weekly limit Quality wise, both were really strong. In terms of speed, they were also pretty close, with both taking roughly 30 minutes to finish, I’m running a lot more tests in parallel right now to see whether there’s actually a meaningful difference between them once you push both models harder

72,108 просмотров • 1 месяц назад

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

102,870 просмотров • 2 месяцев назад

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

Fable 5.1 xHigh vs GLM 5.3 Flash Max With Zai’s current promo, GLM 5.3 Flash is around 58x cheaper than Fable 5.1… and just look at the quality It finished the same task in about half the time, while still delivering a genuinely impressive result 58x cheaper. 2x faster. And the quality is this close That’s honestly crazy, Huge credit to Zhipu for bringing us models this efficient

110,563 просмотров • 2 месяцев назад

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

30,417 просмотров • 24 дней назад

DeepSeek V4.1 Flash-1017 High vs Gemini 4 Argon High, DeepSeek was over 85% cheaper than Argon in this test and finished the task twice as fast, costing less than 0.3 cents through the API, What's even more impressive is how close DeepSeek gets to Argon in terms of quality, especially considering it's a natively multimodal MoE model with just 552B parameters, I still can't get over how efficient this model is, the quality keeps surprising me and the speed makes it even better. I'm now running much more demanding tests that go around three times deeper and take considerably longer, so I'll be sharing more detailed results and benchmarks in a few hours!

DeepSeek V4.1 Flash-1017 High vs Gemini 4 Argon High, DeepSeek was over 85% cheaper than Argon in this test and finished the task twice as fast, costing less than 0.3 cents through the API, What's even more impressive is how close DeepSeek gets to Argon in terms of quality, especially considering it's a natively multimodal MoE model with just 552B parameters, I still can't get over how efficient this model is, the quality keeps surprising me and the speed makes it even better. I'm now running much more demanding tests that go around three times deeper and take considerably longer, so I'll be sharing more detailed results and benchmarks in a few hours!

30,347 просмотров • 26 дней назад

I’ve been testing Muse Spark 1.3 MAX and honestly, it’s insanely good and surprisingly efficient, It just got enabled today and it’s already sitting at 3 on Artificial Analysis. Definitely give it a try, it’s way better than I expected. Meta is seriously cooking right now!

I’ve been testing Muse Spark 1.3 MAX and honestly, it’s insanely good and surprisingly efficient, It just got enabled today and it’s already sitting at 3 on Artificial Analysis. Definitely give it a try, it’s way better than I expected. Meta is seriously cooking right now!

60,124 просмотров • 2 месяцев назад

🚨Pulse Alpha is almost certainly a new model from Thinking Machines, and it's already available for free on OpenCode! I've been testing Pulse Alpha Free Max with the exact same prompt I used for Opus 5.5 and GPT-6 Astra, and it's been running for almost an hour now, while Opus finished in just 24 minutes and Astra took 32 minutes. Maybe it's taking longer because I'm using the highest reasoning setting, but from what I've seen so far, the quality is much better than I expected and I'm really liking the results! I'm still running several more tests in parallel to see how it compares with other frontier models, so I'll have a lot more results to share soon. It's definitely slower in this particular benchmark, but the quality has been a really nice surprise so far, can't wait to see how the final result turns out!

🚨Pulse Alpha is almost certainly a new model from Thinking Machines, and it's already available for free on OpenCode! I've been testing Pulse Alpha Free Max with the exact same prompt I used for Opus 5.5 and GPT-6 Astra, and it's been running for almost an hour now, while Opus finished in just 24 minutes and Astra took 32 minutes. Maybe it's taking longer because I'm using the highest reasoning setting, but from what I've seen so far, the quality is much better than I expected and I'm really liking the results! I'm still running several more tests in parallel to see how it compares with other frontier models, so I'll have a lot more results to share soon. It's definitely slower in this particular benchmark, but the quality has been a really nice surprise so far, can't wait to see how the final result turns out!

11,423 просмотров • 10 дней назад

GPT-6 Pro with sub agents in ChatGPT, This test took more than 90 minutes, and honestly, it’s the most realistic result I’ve gotten from any model so far. Better than Fable 5.1 or anything else I’ve tried, It followed almost every single instruction and got the result nearly perfect, I genuinely think GPT6 Pro mode is being seriously underrated right now, On the ChatGPT x20 plan, we get around 30 prompts a day, roughly 200 per week,For this kind of long, complex task with sub agents, it honestly feels like the best of the best

GPT-6 Pro with sub agents in ChatGPT, This test took more than 90 minutes, and honestly, it’s the most realistic result I’ve gotten from any model so far. Better than Fable 5.1 or anything else I’ve tried, It followed almost every single instruction and got the result nearly perfect, I genuinely think GPT6 Pro mode is being seriously underrated right now, On the ChatGPT x20 plan, we get around 30 prompts a day, roughly 200 per week,For this kind of long, complex task with sub agents, it honestly feels like the best of the best

49,685 просмотров • 1 месяц назад

Just tried Gemini 3.8 Flash and wow, I’m genuinely impressed, It finished everything in under 2 minutes and the quality was way better than I expected, For now it’s only in Chat, but it should be coming to Antigravity and AI Studio later, Really excited to test it there too!

Just tried Gemini 3.8 Flash and wow, I’m genuinely impressed, It finished everything in under 2 minutes and the quality was way better than I expected, For now it’s only in Chat, but it should be coming to Antigravity and AI Studio later, Really excited to test it there too!

55,857 просмотров • 2 месяцев назад