Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Is Opus 5.5 better than GPT-6 Astra at Physical Intelligence "literally" ? put GPT-6 Astra and Claude Opus 5.5 in two Unitree G1s in MuJoCo Ring Fence. Every 2 sim seconds: state → LLM → joint targets → act. Goal: force the other out of the ring, and Astra... show more

Jiafei Duan

7,533 subscribers

39,421 views • 19 hours ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

12 Comments

Mikhail (adhd arc)18 hours ago

losing a robot fight is a brutal new eval category lol

Alexander16 hours ago

Finally, an benchmark that matters ... robot sumo.

automataleague17 hours ago

Or you train your own RL sumo policy in minutes:

H17 hours ago

You may have unlocked a new fighting genre 😂

Sieventer15 hours ago

Mogged

TVoff14 hours ago

fake, latency is the bottleneck

Aryan Dhawan18 hours ago

Lmao this is funny asf

Intercognitive15 hours ago

Deciding model superiority by wrestling is Plato-approved

Jeffrey Li18 hours ago

Opus can barely stand

Jim Bohnslav18 hours ago

you use some kind of harness, or just prompt it for joint angles in text?

Jiafei Duan12 hours ago

Just prompt to output joints

Doug Champion11 hours ago

Please let this be the future of evals

Related Videos

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?

J A Z I I

52,951 views • 1 day ago

Claude Opus 5.5 vs GPT-6 Astra in 3D gaming. From a single prompt: “Build the highest-quality playable PUBG you can.” I went to sleep. When I woke up, both had built a fully playable game🤯 Opus worked for 10 hours end to end, while Astra took just 3.

Claude Opus 5.5 vs GPT-6 Astra in 3D gaming. From a single prompt: “Build the highest-quality playable PUBG you can.” I went to sleep. When I woke up, both had built a fully playable game🤯 Opus worked for 10 hours end to end, while Astra took just 3.

Emm | scenario.com

35,290 views • 22 hours ago

Anthropic cooked with Opus 5.5 🔥🔥 its better than Fable 5.1 and Astra its little close to real one those tiny details: jaguar logo, sensors > 3d model of Waymo autonomous vehicle (Jaguar I-PACE crossover SUV) Opus 5.5 max in Claude code

Harshith

44,060 views • 3 days ago

This looks like a video of the Golden Gate Bridge, but it's actually entirely generated using code by Claude Opus 5.5. From my testing, I think Opus is just as good at building 3D scenes as Astra. 📌 Watch my latest video to see how Opus and Astra compare on this scene and more:

This looks like a video of the Golden Gate Bridge, but it's actually entirely generated using code by Claude Opus 5.5. From my testing, I think Opus is just as good at building 3D scenes as Astra. 📌 Watch my latest video to see how Opus and Astra compare on this scene and more:

Peter Yang

74,238 views • 1 day ago

Opus 4.8 for planning 🤝 GPT 5.5 for implementation Claude is a nicer conversation and /grilling partner than Codex in my experience, but GPT 5.5 on low cranks out higher quality code in fewer tokens. Here's how I divide up the work:

Opus 4.8 for planning 🤝 GPT 5.5 for implementation Claude is a nicer conversation and /grilling partner than Codex in my experience, but GPT 5.5 on low cranks out higher quality code in fewer tokens. Here's how I divide up the work:

Ben Holmes

23,115 views • 3 months ago

Opus 5.5 just made GPT-6 Astra look like the most overpriced model in the room. Same tool. Same footage. Same prompt. Tesseract by Mirage ran both builds back to back, nothing else touched. Opus 5.5: $19.82. GPT-6 Astra: $161.54. Nobody could tell the two outputs apart without checking the invoice. No sharper detail, no cleaner motion, nothing that justified an extra $140. This is the part of the AI race nobody wants to say out loud. Model pricing has stopped tracking model quality. Increasingly you are paying for a name attached to the output, not for anything the video itself proves.

Opus 5.5 just made GPT-6 Astra look like the most overpriced model in the room. Same tool. Same footage. Same prompt. Tesseract by Mirage ran both builds back to back, nothing else touched. Opus 5.5: $19.82. GPT-6 Astra: $161.54. Nobody could tell the two outputs apart without checking the invoice. No sharper detail, no cleaner motion, nothing that justified an extra $140. This is the part of the AI race nobody wants to say out loud. Model pricing has stopped tracking model quality. Increasingly you are paying for a name attached to the output, not for anything the video itself proves.

Zentrix⌚️

22,870 views • 23 hours ago

The team behind AI/ML API tested the new Claude Opus 5.5 against GPT-6 Sol. These tests involved generating a set of one-shot 3D scene prompts, starting with an "animated fish school." Across four scenes, Opus 5.5 produced more detailed renders at a total cost of $4.37, while GPT-6 Sol came in at $0.34, according to their results.

The team behind AI/ML API tested the new Claude Opus 5.5 against GPT-6 Sol. These tests involved generating a set of one-shot 3D scene prompts, starting with an "animated fish school." Across four scenes, Opus 5.5 produced more detailed renders at a total cost of $4.37, while GPT-6 Sol came in at $0.34, according to their results.

🚨 AI News | TestingCatalog

32,072 views • 1 day ago

Check out side-by-side outputs generated on Arena from Claude Opus 5.5 by Anthropic and GPT-6 Sol by OpenAI. Scores for Claude Opus 5.5 are coming soon. Real-world tasks from our global community of users power the Arena leaderboards. Head to Arena now to test it out, and stay tuned!

Check out side-by-side outputs generated on Arena from Claude Opus 5.5 by Anthropic and GPT-6 Sol by OpenAI. Scores for Claude Opus 5.5 are coming soon. Real-world tasks from our global community of users power the Arena leaderboards. Head to Arena now to test it out, and stay tuned!

Arena.ai

66,838 views • 13 hours ago

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

atomic.chat

132,609 views • 16 days ago

GPT-6 Astra is insanely good at blueprint-to-architecture. We gave it one floor plan > GPT-6 Astra generated the scene code > Higgsfield built the location model in Blender and rendered it with Cycles. The whole pipeline runs end-to-end on Higgsfield Supercomputer.

GPT-6 Astra is insanely good at blueprint-to-architecture. We gave it one floor plan > GPT-6 Astra generated the scene code > Higgsfield built the location model in Blender and rendered it with Cycles. The whole pipeline runs end-to-end on Higgsfield Supercomputer.

Higgsfield AI 🧩

33,419 views • 18 days ago

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

hiraeth

40,216 views • 19 days ago

GPT-6 Astra is my favorite model of all time and it's not really close It's a step function similar to Fable or Opus 4.5, the computer use stuff has unlocked truly novel workflows

GPT-6 Astra is my favorite model of all time and it's not really close It's a step function similar to Fable or Opus 4.5, the computer use stuff has unlocked truly novel workflows

Ben Davis

39,248 views • 19 days ago

I recreated Townscaper with GPT-6 Astra using Three.js on Happycapy The result is surprisingly close to the original, and it took way less time than I expected 🤯 Astra is seriously good at this kind of 3D coding task.

I recreated Townscaper with GPT-6 Astra using Three.js on Happycapy The result is surprisingly close to the original, and it took way less time than I expected 🤯 Astra is seriously good at this kind of 3D coding task.

Min Zhou

10,531 views • 16 days ago

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

Salio

407,920 views • 10 days ago

GPT 6 Astra + Computer Use put this track together in GarageBand in about 18 minutes. Make a video game soundtrack similar to Ori and the will of the wisps.

GPT 6 Astra + Computer Use put this track together in GarageBand in about 18 minutes. Make a video game soundtrack similar to Ori and the will of the wisps.

Dev Ed

21,051 views • 17 days ago

this is f*cking gold HOW TO USE GPT6-ASTRA & Fable 5.1 FOR FREE Based on my tests, this is definitely the genuine 100% version of the Astra: > ultra-fast performance > a large number of tokens > not many people How to get: 1. go to: 2. log in via Gmail or GitHub 3. get API key 4. start using Other available models: Qwen3.8 27B, DeepSeek V4 Flash, GPT-5.6 Luna, Claude Fable 5.1, GPT-6 Astra and many other..

this is f*cking gold HOW TO USE GPT6-ASTRA & Fable 5.1 FOR FREE Based on my tests, this is definitely the genuine 100% version of the Astra: > ultra-fast performance > a large number of tokens > not many people How to get: 1. go to: 2. log in via Gmail or GitHub 3. get API key 4. start using Other available models: Qwen3.8 27B, DeepSeek V4 Flash, GPT-5.6 Luna, Claude Fable 5.1, GPT-6 Astra and many other..

kaize

32,778 views • 18 days ago

How to edit videos with GPT-6 Astra: 1. Install the ChatCut plugin in ChatGPT/Codex 2. Select GPT-6 Astra 3. Upload your footage 4. Describe the video you want Astra understands your footage and edits it directly in ChatCut. Every cut, caption, and motion graphic stays editable on a real timeline. This screen recording shows the entire setup and a short-video edit from start to finish. Comment “Chat” to get the plugin.

How to edit videos with GPT-6 Astra: 1. Install the ChatCut plugin in ChatGPT/Codex 2. Select GPT-6 Astra 3. Upload your footage 4. Describe the video you want Astra understands your footage and edits it directly in ChatCut. Every cut, caption, and motion graphic stays editable on a real timeline. This screen recording shows the entire setup and a short-video edit from start to finish. Comment “Chat” to get the plugin.

ChatCut

43,445 views • 14 days ago

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Someone gave GPT-6 and Fable 5.1 access to Canva. One smoked the other (it's not even close). Claude Fable 5.1 is on the left. GPT-6 Astra is on the right. The gap is not small. It comes down to one test (ARC-AGI 3). It drops a model into a game with no instructions and makes it work them out. Astra solved levels in fewer moves than you or I would, 96% of the time. Claude Opus 5 managed less than half of that. That's why everyone is shouting about AGI again. You can turn this on yourself in about two minutes: 1. Open the ChatGPT desktop app, switch to Work. 2. Go to Plugins, then Computer Use. Install it. 3. Switch on the server and skill toggles. 4. Allow Screen Recording and Accessibility. 5. Point it at one app and ask it do something. I wrote up the full Claude → Codex migration. Access it here → Repost ♻️ to help someone in your network.

Charlie Hills

38,355 views • 17 days ago

GPT-6 Astra vs DeepSeek V4.1 Flash in Three.js. Same kind of task, two completely different approaches. The visual difference alone is pretty interesting. Source footage and original material: OpenDesign

GPT-6 Astra vs DeepSeek V4.1 Flash in Three.js. Same kind of task, two completely different approaches. The visual difference alone is pretty interesting. Source footage and original material: OpenDesign

Token Gremlin

44,432 views • 13 days ago

GPT-6 Astra is now the best-performing frontier model for antibody developability prediction in our benchmark. 🧬 Finding an antibody that binds is only the beginning. Will it aggregate? Will it stay stable? Can it actually behave like a drug? GPT-6 Astra predicts these developability properties better than the other frontier models we tested. 🤯 And yes, the interactive visualization showing how an antibody actually works was also built with Astra in about 1 hour. This model looks seriously powerful. Congrats gbt Sam Altman #insilicoSOTAFM

GPT-6 Astra is now the best-performing frontier model for antibody developability prediction in our benchmark. 🧬 Finding an antibody that binds is only the beginning. Will it aggregate? Will it stay stable? Can it actually behave like a drug? GPT-6 Astra predicts these developability properties better than the other frontier models we tested. 🤯 And yes, the interactive visualization showing how an antibody actually works was also built with Astra in about 1 hour. This model looks seriously powerful. Congrats gbt Sam Altman #insilicoSOTAFM

Andrew Aiginin

310,484 views • 13 days ago