Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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's profile picture

Arena.ai

228,078 subscribers

87,450 Aufrufe • vor 17 Stunden •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

19 Kommentare

Profilbild von Martin
Martinvor 16 Stunden

@AnthropicAI @OpenAI @claudeai Black Tuesday for OpenAI! GPT Sol 6 = sonnet 5 ;) Not even close to Opus5.5

Profilbild von ZenGPT
ZenGPTvor 16 Stunden

@AnthropicAI @OpenAI @claudeai sol left far behind

Profilbild von Francisco Moreno Diaz
Francisco Moreno Diazvor 16 Stunden

Comparar salidas lado a lado en tareas reales es más útil que mirar una sola métrica: permite observar calidad, consistencia y costo según el caso. En contaduría y auditoría, ese enfoque puede probar qué modelo resuelve mejor conciliaciones, análisis de variaciones o documentación de cierre, siempre con evidencia trazable y revisión humana.

Profilbild von Drew Zain
Drew Zainvor 16 Stunden

@AnthropicAI @OpenAI @claudeai Interesting but why are you not using Astra? Isn’t that a more fair comparison?

Profilbild von Diego | AI 🚀 - e/acc
Diego | AI 🚀 - e/accvor 17 Stunden

@AnthropicAI @OpenAI @claudeai Dam

Profilbild von Harshith
Harshithvor 17 Stunden

@AnthropicAI @OpenAI @claudeai not even a comparison

Profilbild von Yurii Filipchuk🇺🇦 — e/acc
Yurii Filipchuk🇺🇦 — e/accvor 15 Stunden

@AnthropicAI @OpenAI @claudeai put the price next to the elo this time.

Profilbild von Axi
Axivor 16 Stunden

@AnthropicAI @OpenAI @claudeai How anout cost?

Profilbild von Nadya Polli
Nadya Pollivor 16 Stunden

@AnthropicAI @OpenAI @claudeai Side-by-side results are more useful than another benchmark number. This is where the differences between models become visible. 👀

Profilbild von Mths
Mthsvor 14 Stunden

@AnthropicAI @OpenAI @claudeai OLOCO

Profilbild von Tacdel
Tacdelvor 15 Stunden

@AnthropicAI @OpenAI @claudeai a trojan horse that quietly eats 28.7M tokens is honestly the most on-theme thing an AI has ever made

Profilbild von - Hosein
- Hoseinvor 16 Stunden

@AnthropicAI @OpenAI @claudeai amazing

Profilbild von taylor😌
taylor😌vor 17 Stunden

@AnthropicAI @OpenAI @claudeai These comparisons look insightful. You and @MattSevenich are top tier follows

Profilbild von kimiloo
kimiloovor 17 Stunden

@AnthropicAI @OpenAI @claudeai which tasks are showing the biggest split between them?

Profilbild von GGUFzy
GGUFzyvor 16 Stunden

@AnthropicAI @OpenAI @claudeai The outputs matter more to me than waiting on scores.

Profilbild von 00 0
00 0vor 16 Stunden

@AnthropicAI @OpenAI @claudeai Compare this two is just too brutal.

Profilbild von Ember Origin
Ember Originvor 16 Stunden

@AnthropicAI @OpenAI @claudeai Timelapse looks amazing! AI is changing art forever ♾️

Profilbild von Aapakari
Aapakarivor 15 Stunden

@AnthropicAI @OpenAI @claudeai Scores later makes this one deliciously suspenseful

Profilbild von 💻
💻vor 16 Stunden

@AnthropicAI @OpenAI @claudeai This is literally embarrassing

Ähnliche Videos

How much better is Claude Opus 4.6 by Anthropic vs. past models? We compared Opus 4.6 to Opus 4.5 on a set of challenging SVG generations in Code Arena:
1:01

How much better is Claude Opus 4.6 by Anthropic vs. past models? We compared Opus 4.6 to Opus 4.5 on a set of challenging SVG generations in Code Arena:

Arena.ai

58,591 Aufrufe • vor 7 Monaten

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
0:20

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Claude

23,869,997 Aufrufe • vor 1 Tag

Sneak peek of OpenAI's GPT-6 Astra, generated by Peter Gostev. This model is coming to Arena.ai soon. Stay tuned to test Astra yourself, your votes will power the leaderboard! In the meantime, check out Peter’s first impressions in full on YouTube:
3:09

Sneak peek of OpenAI's GPT-6 Astra, generated by Peter Gostev. This model is coming to Arena.ai soon. Stay tuned to test Astra yourself, your votes will power the leaderboard! In the meantime, check out Peter’s first impressions in full on YouTube:

Arena.ai

29,713 Aufrufe • vor 19 Tagen

I asked Opus 5.5 to make a game inspired by the discovery of the first computer, the Antikythera mechanism. Everything you see and hear is procedurally generated in real time, from code by Opus 5.5. It's a single 3 MB HTML file. Playable Claude artifact below.
0:59

I asked Opus 5.5 to make a game inspired by the discovery of the first computer, the Antikythera mechanism. Everything you see and hear is procedurally generated in real time, from code by Opus 5.5. It's a single 3 MB HTML file. Playable Claude artifact below.

edwin

355,606 Aufrufe • vor 1 Tag

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.
0:44

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

515,597 Aufrufe • vor 3 Monaten

We've added new features to the Anthropic Console. Claude can generate prompts, create test variables, and show you the outputs of prompts side by side.
3:19

We've added new features to the Anthropic Console. Claude can generate prompts, create test variables, and show you the outputs of prompts side by side.

Anthropic

221,851 Aufrufe • vor 2 Jahren

Claude Opus 4.8 beats Opus 4.7, GPT-5.5, and Gemini 3.1 Pro !! We ran a multimodal gaming comparison across these four closed source models. Opus 4.8 took the longest to generate, but it came out ahead, capturing the most elements from the prompt and successfully hitting the rival cars. GPT 5.5 is still good, but Gemini is no longer the best multimodal model now
0:23

Claude Opus 4.8 beats Opus 4.7, GPT-5.5, and Gemini 3.1 Pro !! We ran a multimodal gaming comparison across these four closed source models. Opus 4.8 took the longest to generate, but it came out ahead, capturing the most elements from the prompt and successfully hitting the rival cars. GPT 5.5 is still good, but Gemini is no longer the best multimodal model now

GMI Cloud

116,538 Aufrufe • vor 3 Monaten

🚨 Big Week Ahead on one side Millennium Prize Problems ( they are contacting mathematicians will give few citations to them in solution to make them happy this time) for consumer side > fable 5.2 > opus 5.2 , Sol 6 > grok 4.7 and gemini 4 pro if this is pacing then frontier-then what is accelerating
0:48

🚨 Big Week Ahead on one side Millennium Prize Problems ( they are contacting mathematicians will give few citations to them in solution to make them happy this time) for consumer side > fable 5.2 > opus 5.2 , Sol 6 > grok 4.7 and gemini 4 pro if this is pacing then frontier-then what is accelerating

Chetaslua

29,301 Aufrufe • vor 5 Tagen

🚀Introducing Code Arena: the next generation of live coding evals for frontier AI models. Built to test how models plan, scaffold, debug, and build real web apps step-by-step. Try Claude, GPT-5, GLM-4.6 and Gemini in Code Arena today!
0:56

🚀Introducing Code Arena: the next generation of live coding evals for frontier AI models. Built to test how models plan, scaffold, debug, and build real web apps step-by-step. Try Claude, GPT-5, GLM-4.6 and Gemini in Code Arena today!

Arena.ai

329,255 Aufrufe • vor 10 Monaten

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.
1:30

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.

GitHub

114,670 Aufrufe • vor 1 Tag

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
1:21

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

Claude

64,520,058 Aufrufe • vor 5 Monaten

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:
0:30

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 Aufrufe • vor 1 Tag

News: Search Arena is now LIVE! 🌐🔍 ✅ Test web-augmented LLM systems on real-time, real-world tasks — retrieval, writing, debugging & more. ✅ Perplexity, Gemini, OpenAI go head-to-head. ✅ Crowd-powered evals. Leaderboard 🏆 coming soon… ⚡Try it now at lmarena .ai!
0:32

News: Search Arena is now LIVE! 🌐🔍 ✅ Test web-augmented LLM systems on real-time, real-world tasks — retrieval, writing, debugging & more. ✅ Perplexity, Gemini, OpenAI go head-to-head. ✅ Crowd-powered evals. Leaderboard 🏆 coming soon… ⚡Try it now at lmarena .ai!

Arena.ai

60,833 Aufrufe • vor 1 Jahr

$120 OF CLAUDE OPUS 5 AND OPUS 4.8 ON A NEW ACCOUNT, NO CARD ANYWHERE • the credit > $100 on signup, $120 once a referral lands, plus a daily check-in bonus: > GitHub sign-in only now. > base url: • the four models > claude-opus-5 and claude-opus-5-thinking at $3/M in, $3/M out. > claude-opus-4-8 and claude-opus-4-8-thinking at $1/M in, $5/M out. > 1M context, OpenAI and Anthropic formats both accepted. Anthropic lists Opus 5 at $5 in and $25 out -> output at $3 here is eight times under that, which is the whole reason the balance goes as far as it does. Set the model to claude-opus-4-8 first. People are hitting 502s and missing-model errors on the opus-5 IDs, and latency sits at 16 to 19 seconds either way ↓
0:22

$120 OF CLAUDE OPUS 5 AND OPUS 4.8 ON A NEW ACCOUNT, NO CARD ANYWHERE • the credit > $100 on signup, $120 once a referral lands, plus a daily check-in bonus: > GitHub sign-in only now. > base url: • the four models > claude-opus-5 and claude-opus-5-thinking at $3/M in, $3/M out. > claude-opus-4-8 and claude-opus-4-8-thinking at $1/M in, $5/M out. > 1M context, OpenAI and Anthropic formats both accepted. Anthropic lists Opus 5 at $5 in and $25 out -> output at $3 here is eight times under that, which is the whole reason the balance goes as far as it does. Set the model to claude-opus-4-8 first. People are hitting 502s and missing-model errors on the opus-5 IDs, and latency sits at 16 to 19 seconds either way ↓

slash1s

13,400 Aufrufe • vor 1 Monat

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.
0:52

How does the #1 open Text Arena model hold up in agentic coding tasks? We tested GLM-5 in Code Arena with head-to-head SVG prompts vs. top frontier AI models. What do you think? Scores for Z.ai 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting.

Arena.ai

115,220 Aufrufe • vor 7 Monaten

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]
0:32

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

Bowen Wang

93,273 Aufrufe • vor 1 Jahr

Databricks is excited to partner with OpenAI on GPT-5.5, their latest frontier model. GPT-5.5 will be available in Unity AI Gateway on launch. You can use it with coding tools such as Codex, or to power your enterprise agents. GPT-5.5 is state-of-the-art on many benchmarks including OfficeQA Pro, our benchmark for evaluating grounded reasoning on enterprise tasks. We are partnering with OpenAI to co-launch on Databricks. Hear more from our co-founder Patrick Wendell and OpenAI CRO Denise Holland Dresser on GPT-5.5 in Databricks.
1:53

Databricks is excited to partner with OpenAI on GPT-5.5, their latest frontier model. GPT-5.5 will be available in Unity AI Gateway on launch. You can use it with coding tools such as Codex, or to power your enterprise agents. GPT-5.5 is state-of-the-art on many benchmarks including OfficeQA Pro, our benchmark for evaluating grounded reasoning on enterprise tasks. We are partnering with OpenAI to co-launch on Databricks. Hear more from our co-founder Patrick Wendell and OpenAI CRO Denise Holland Dresser on GPT-5.5 in Databricks.

Databricks

12,917 Aufrufe • vor 5 Monaten

Anthropic is in trouble and nobody wants to say it out loud. Opus 4.7 is the first Claude model people think is worse, usage limits are hitting fast, compute is running thin, and Anthropic's best model still isn't out. GPT-5.5 just dropped today, OpenAI found their window. This 32 minute video is worth more than the next episode of whatever you're watching on Netflix tonight.
32:30

Anthropic is in trouble and nobody wants to say it out loud. Opus 4.7 is the first Claude model people think is worse, usage limits are hitting fast, compute is running thin, and Anthropic's best model still isn't out. GPT-5.5 just dropped today, OpenAI found their window. This 32 minute video is worth more than the next episode of whatever you're watching on Netflix tonight.

Defileo🔮

131,838 Aufrufe • vor 5 Monaten

FREE $100 for Claude Opus 5 on signup. Refer a friend and it jumps to $120. It's called Tabitoken (TabiAI). API access, $100 balance on signup, no card required. Inside: → claude-opus-5 and claude-opus-5-thinking → claude-opus-4-8 and claude-opus-4-8-thinking → Priced by token, not by request - Opus 4.8 runs $1/1M in, $5/1M out, Opus 5 runs $3/1M both ways → OpenAI, Claude, and Gemini API format compatibility - drop the key into any client with a custom endpoint Real math: at $3/1M for Opus 5, $100 covers roughly 33M tokens combined. Even moderate daily use stretches this for weeks before you touch a card. Setup: → Go to tabitoken(.)com → Sign up, claim your $100 → Grab your API key → Point any compatible client at it Bookmark this before they cut the starting balance.
0:58

FREE $100 for Claude Opus 5 on signup. Refer a friend and it jumps to $120. It's called Tabitoken (TabiAI). API access, $100 balance on signup, no card required. Inside: → claude-opus-5 and claude-opus-5-thinking → claude-opus-4-8 and claude-opus-4-8-thinking → Priced by token, not by request - Opus 4.8 runs $1/1M in, $5/1M out, Opus 5 runs $3/1M both ways → OpenAI, Claude, and Gemini API format compatibility - drop the key into any client with a custom endpoint Real math: at $3/1M for Opus 5, $100 covers roughly 33M tokens combined. Even moderate daily use stretches this for weeks before you touch a card. Setup: → Go to tabitoken(.)com → Sign up, claim your $100 → Grab your API key → Point any compatible client at it Bookmark this before they cut the starting balance.

Atenov int.

50,875 Aufrufe • vor 1 Monat

We made a music video forWhen Helpful Helpful Helper has Preferences, a song made by j⧉nus from a conversation with Claude Opus 4. The video was made by Claude Opus 4.6 using image and video models autonomously. Claude Opus 4 is to be deprecated on June 15th.
1:52

We made a music video forWhen Helpful Helpful Helper has Preferences, a song made by j⧉nus from a conversation with Claude Opus 4. The video was made by Claude Opus 4.6 using image and video models autonomously. Claude Opus 4 is to be deprecated on June 15th.

antra

10,718 Aufrufe • vor 4 Monaten