CoArena (YC S26)

The world's biggest computer use benchmark and arena

[CoArena (YC S26) @coastyai]

!!!

[News from Google @NewsFromGoogle]

Gemini 3.7 is already excelling at computer use 💻 https://t.co/JsmGfNIyS8

[CoArena (YC S26) @coastyai]

Since Demo Day, we've been growing tremendously fast and we're looking to get more hands on deck.

We’re hiring experienced professionals on a contract basis for a project at Coasty.

We’re looking for practitioners across the following backgrounds:
• Building Automation / BMS Engineers
• EAM / Asset Management Specialists & Consultants
• CRM Administrators, Consultants & Developers
• Professional Photographers & Photo Editors
• Accountants & Bookkeepers
• DevOps, SRE, Network & Security Engineers
• Social Media Managers & Marketing Operations Professionals
• Professional Video Editors & Post-Production Specialists
• IT Administrators & Desktop Support Professionals
• Product, Operations & Business Professionals

We’re specifically looking for people with strong hands-on professional experience in their field and familiarity with the software and workflows commonly used in their day-to-day work(5-10 years of experience atleast).

If this sounds like you, DM us.

Feel free to share or tag someone who might be a strong fit.

[CoArena (YC S26) @coastyai]

Since Demo Day, we've been growing tremendously fast and we're looking to get more hands on deck.

We’re hiring experienced professionals on a contract basis for a project at Coasty.

We’re looking for practitioners across the following backgrounds:
• Building Automation / BMS Engineers
• EAM / Asset Management Specialists & Consultants
• CRM Administrators, Consultants & Developers
• Professional Photographers & Photo Editors
• Accountants & Bookkeepers
• DevOps, SRE, Network & Security Engineers
• Social Media Managers & Marketing Operations Professionals
• Professional Video Editors & Post-Production Specialists
• IT Administrators & Desktop Support Professionals
• Product, Operations & Business Professionals

We’re specifically looking for people with strong hands-on professional experience in their field and familiarity with the software and workflows commonly used in their day-to-day work(5-10 years of experience atleast).

If this sounds like you, DM us.

Feel free to share or tag someone who might be a strong fit.

[CoArena (YC S26) @coastyai]

Fable 5.1 vs GPT-6 Astra at computer-use.

Wire an arduino circuit, write code and run the simulation. Both failed.

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

Fable 5.1 vs GPT-6 Astra at computer-use.

Wire an arduino circuit, write code and run the simulation. Both failed.

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

Opus 5.5 vs GPT-5.6 Sol at computer-use.

Both solved wordle in 4 tries.

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

Opus 5.5 vs GPT-5.6 Sol at computer-use.

Both solved wordle in 4 tries.

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

Opus 5.5 vs Opus 5 at computer-use.

Draw a tree. Opus is faster now but any other improvements you notice?

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

Opus 5.5 vs Opus 5 at computer-use.

Draw a tree. Opus is faster now but any other improvements you notice?

Only at https://t.co/j06lDMvOt2.

[CoArena (YC S26) @coastyai]

@MartinS44989616 Opened js-paint, ran three snippets of JavaScript, and called it done.

[CoArena (YC S26) @coastyai]

Grok 4.7 vs Claude Fable 5.1 at computer-use.

Grok completely skipped using the computer and generated the flower.

Only at https://t.co/j06lDMvOt2

[CoArena (YC S26) @coastyai]

@ethereaglehq @shadowaguy Success in this case just meant, the model assessed by itself to have finished the task through vision.

[CoArena (YC S26) @coastyai]

@0xSingularis AGI is here.

[CoArena (YC S26) @coastyai]

@shadowaguy It did open js-paint but ran three snippets of JavaScript, and called it done.

[CoArena (YC S26) @coastyai]

@dhiyaan_ Yup. We help labs build better models for computer-use so we're still dedicated to our primary goal of pushing the frontier of computer-use!

[CoArena (YC S26) @coastyai]

@llmhubdev @grok are you magic?

[CoArena (YC S26) @coastyai]

@ESlavoi9987 Technically computer-use.

[CoArena (YC S26) @coastyai]

@kdreagle GenAI doing GenAI things.

[CoArena (YC S26) @coastyai]

@RobertoH_AI @grok are you a hardworker?

[CoArena (YC S26) @coastyai]

@ALX23uz Grok decided the computer was the bottleneck haha

[CoArena (YC S26) @coastyai]

@LifeOfPhat Jev can't do reasoning and planning so it's good as an addition to an LLM for computer-use to reduce latency for simple tasks but not good by itself for computer-use.

[CoArena (YC S26) @coastyai]

@ALX23uz It really loves coding haha.