# ![@arena Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1641378826537295874.png) @arena Arena.ai

Arena.ai posts on X about model, ai, leaderboard, agentic the most. They currently have [-------] followers and [---] posts still getting attention that total [------] engagements in the last [--] hours.

### Engagements: [------] [#](/creator/twitter::1641378826537295874/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1641378826537295874/c:line/m:interactions.svg)

- [--] Week [----------] +164%
- [--] Month [----------] +875%
- [--] Months [----------] +131%
- [--] Year [----------] +122%

### Mentions: [--] [#](/creator/twitter::1641378826537295874/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1641378826537295874/c:line/m:posts_active.svg)

- [--] Week [---] +80%
- [--] Month [---] +24%
- [--] Months [---] +243%
- [--] Year [---] +239%

### Followers: [-------] [#](/creator/twitter::1641378826537295874/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1641378826537295874/c:line/m:followers.svg)

- [--] Week [-------] +2.30%
- [--] Month [-------] +4%
- [--] Months [-------] +46%
- [--] Year [-------] +94%

### CreatorRank: [-------] [#](/creator/twitter::1641378826537295874/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1641378826537295874/c:line/m:influencer_rank.svg)

### Social Influence

**Social category influence**
[technology brands](/list/technology-brands)  37.61% [social networks](/list/social-networks)  7.34% [celebrities](/list/celebrities)  1.83% [finance](/list/finance)  0.92% [vc firms](/list/vc-firms)  0.92% [stocks](/list/stocks)  0.92%

**Social topic influence**
[model](/topic/model) #538, [ai](/topic/ai) 20.18%, [leaderboard](/topic/leaderboard) #112, [agentic](/topic/agentic) #128, [in the](/topic/in-the) #5369, [open ai](/topic/open-ai) #1315, [arena](/topic/arena) #253, [to the](/topic/to-the) 9.17%, [xai](/topic/xai) #25, [math](/topic/math) #2773

**Top accounts mentioned or mentioned by**
[@chaos2cured](/creator/undefined) [@xai](/creator/undefined) [@openai](/creator/undefined) [@googledeepmind](/creator/undefined) [@ml_angelopoulos](/creator/undefined) [@anthropicai](/creator/undefined) [@xais](/creator/undefined) [@grok](/creator/undefined) [@chetaslua](/creator/undefined) [@teksedge](/creator/undefined) [@bflml](/creator/undefined) [@zaiorg](/creator/undefined) [@harjjotsinghh](/creator/undefined) [@henkpoley](/creator/undefined) [@kimimoonshot](/creator/undefined) [@darwinc12041](/creator/undefined) [@openais](/creator/undefined) [@elonmusk](/creator/undefined) [@hercilio_game](/creator/undefined) [@elaina43114880](/creator/undefined)

**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/$googl)
### Top Social Posts
Top posts by engagements in the last [--] hours

"Claude Opus [---] thinking has landed at #1 across Code and Text Arena Both thinking and non-thinking have taken the top [--] spots across both leaderboards. @AnthropicAI now has [--] of the top [--] models in the Code Arena. A few highlights: - #1 Code Arena: scoring [----] - #1 Text Arena: scoring [----] - In Code Arena: Claude Opus [---] takes #1 & #2; Claude Opus [---] takes #3 & #5 Congrats to the @AnthropicAI team on another milestone 🚨BREAKING: Claude Opus [---] by @AnthropicAI is now #1 across Code Text and Expert Arena Opus [---] shows significant gains across the board: - #1 Code Arena: +106 score vs"  
[X Link](https://x.com/arena/status/2020956227795288132)  2026-02-09T20:21Z 129K followers, 49.2K engagements


"AI needs better evaluations. Today were announcing Arenas Academic Partnerships Program to fund independent academic research in AI evaluation and measurement. Up to $50K/project. Q1 Deadline: March [--] [----]. See more in thread for details and how to apply 👇"  
[X Link](https://x.com/arena/status/2021268433619374336)  2026-02-10T17:02Z 129K followers, 57.3K engagements


"The new @xAI Grok-Imagine-Image model is a Pareto-optimal model in Image Arena: The Pareto frontier tells us which model has the highest Arena score at each price point. @xAis latest models have improved the frontier giving optimal performance in the mid-price tier. For a wide range of prices between 2c and 8c per image @elonmusks @xAI has the leading model delivering the maximum performance. Top models on the Pareto frontier for Image Arena (Single Image Edit): - @OpenAI: GPT-Image-1.5-high-fidelity - @xAI: Grok Imagine Image Pro - @xAI: Grok Imagine Image - @bfl_ml: Flux [--] Klein 9B -"  
[X Link](https://x.com/arena/status/2020215931646120004)  2026-02-07T19:19Z 129K followers, 9.9M engagements


"GLM-5 from @Zai_org just climbed to #1 among open models in Text Arena #1 open model on par with claude-sonnet-4.5 & gpt-5.1-high #11 overall; scoring [----] +11pts over GLM-4.7 Test it out in the Code Arena and keep voting well see how GLM-5 performs for agentic coding tasks next Congrats to the @Zai_org for this amazing achievement. Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5 it scales from 355B params (32B active) to 744B (40B active) with pre-training data growing from 23T to"  
[X Link](https://x.com/arena/status/2021725350481526904)  2026-02-11T23:17Z 129K followers, 158.5K engagements


"GLM-5 by @Zai_org is now the #1 open model in Code Arena tied with Kimi-K2.5-Thinking Overall #6 on par with Gemini-3-pro 100+pts below Claude-Opus-4.6 in agentic webdev tasks. Congrats to the @Zai_org GLM team on the new milestone 👏 Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5 it scales from 355B params (32B active) to 744B (40B active) with pre-training data growing from 23T to 28.5T tokens. https://t.co/uGYQUjIbbs Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5"  
[X Link](https://x.com/arena/status/2021996281141629219)  2026-02-12T17:14Z 129K followers, 27.4K engagements


"Now that you've seen a peek at what these models can do check out the leaderboards to see how they stack up with real world use from millions of real people using AI around the world: http://arena.ai/leaderboard http://arena.ai/leaderboard"  
[X Link](https://x.com/arena/status/2022713022608003363)  2026-02-14T16:42Z 129K followers, [----] engagements


"Woah another exciting update from Chatbot Arena❤🔥 The results for @xAIs sus-column-r (Grok [--] early version) are now public** With over [-----] community votes sus-column-r has secured the #3 spot on the overall leaderboard even matching GPT-4o It excels in Coding (#2) Hard Prompts (#4) and Math (#2). Congratulations to @xAI on this impressive debut for Grok [--] More plots below👇 **Note: We post its early result on twitter. The official update for Grok [--] coming soon. https://t.co/2QIqApWk0Y https://t.co/2QIqApWk0Y"  
[X Link](https://x.com/anyuser/status/1823599819551858830)  2024-08-14T05:57Z 128.9K followers, 6.1M engagements


"Introducing Prompt-to-leaderboard (P2L): a real-time LLM leaderboard tailored exactly to your use case P2L trains an LLM to generate "prompt-specific" leaderboards so you can input a prompt and get a leaderboard specifically for that prompt. The model is trained on the 2M human preference votes from Chatbot Arena. P2L Highlights: 🔹Instant leaderboard for any prompt 🗿 🔹Optimal model routing (hit #1 on Chatbot Arena in Jan [----] with [----] score 🧏) 🔹Fine-grained model strength & weakness analysis 🤓 Check out our demo and thread below for more details"  
[X Link](https://x.com/arena/status/1894767009977811256)  2025-02-26T15:10Z 128.9K followers, 123.3K engagements


"📢Were excited to share that weve raised $100M in seed funding to support LMArena and continue our research on reliable AI. Led by @a16z and UC Investments (@UofCalifornia) we're proud to have the support of those that believe in both the science and the mission. Were focused on building a neutral open community-driven platform that helps the world understand and improve the performance of AI models on real queries from real users. Also big news is coming next week👀 We're relaunching LMArena with a whole new look built directly with community feedback from the ground up 🧱 Link in thread."  
[X Link](https://x.com/arena/status/1925241333310189804)  2025-05-21T17:24Z 128.9K followers, 435.5K engagements


"🚨 Breaking News: Grok 4's result is now live With 4k+ community votes xAIs Grok-4 tied for #3 overall in Text Arena a huge leap from Grok-3. It scores Top-3 across all categories (#1 in Math #2 in Coding #3 in Hard Prompts). Detailed analysis in the thread 🧵"  
[X Link](https://x.com/arena/status/1945146348203905063)  2025-07-15T15:40Z 128.9K followers, 487.4K engagements


"Our Image Edit Arena now has more data around real-world use. It now has two distinct leaderboards: 🖼 Single-Image Edit: ranks models on single-image tasks 🔢 Multi-Image Edit: ranks models on multi-image tasks This gives us a more accurate view of model performance across distinct image editing use cases from simple edits to multi-image reasoning. Check out some initial insights in thread 🧵"  
[X Link](https://x.com/arena/status/2014749280146481412)  2026-01-23T17:17Z 126.7K followers, 12.1K engagements


"From singleimage edit to multiimage edit the leader flips: @OpenAIs top model is overtaken by @GoogleDeepmindss Gemini Pro. 🔹Leader change: ChatGPT Image (Latest) goes #1 - #3 while Gemini [--] Pro Image 2K (NanoBanana Pro) goes #2 - #1. 🔹Biggest rise: FLUX-2-Flex jumps #19 - #12 (up [--] places). 🔹Smallmodel mover: FLUX-2-Klein 4B climbs #22 - #17 (up [--] places). 🔹Biggest drops: Seedream-4 2K slides #7 - #14 (down [--] places) and Qwen Image Edit (2511) slips #11 - #16 (down [--] places) Toggle between the two to see the differences for yourself at: https://lmarena.ai/leaderboard/image-edit"  
[X Link](https://x.com/arena/status/2014749281757036877)  2026-01-23T17:17Z 126.7K followers, [----] engagements


"Kimi K2.5 lands in the top [--] for Coding category ranking #7 overall"  
[X Link](https://x.com/arena/status/2016294725813465114)  2026-01-27T23:38Z 127.2K followers, 87K engagements


"📰📣Tencent's Hunyuan-Image-3.0-Instruct is officially open sourced making this the #1 open model in the Image Edit Arena It ranks #7 overall closely matching Nano-Banana and Seedream-4.5. Incredible news for the AI community and congrats to the @TencentHunyuan team. HunyuanImage 3.0-Instruct is officially open-sourced Freshly ranked in the global tier-1 on @arenas Image Edit leaderboard it stands as the world's strongest open-source Image-to-Image model setting a new SOTA for the community 🏆 🔗Github: https://t.co/ucSdq0WaOL 🤗Hugging https://t.co/KWYrPEX9ei HunyuanImage 3.0-Instruct is"  
[X Link](https://x.com/arena/status/2016532356128239994)  2026-01-28T15:22Z 127.1K followers, 10.4K engagements


"🚨BREAKING: Kimi K2.5 Thinking by @Kimi_Moonshot is the #1 open model for Vision Arena Highlights: - #1 open model in Vision (+40pt over the next open model) - #6 overall (Qwen3-vl-235b-a22b-instruct is next open model at #18) This is the only open model in the Top [--]. Congrats to the @Kimi_Moonshot team for this incredible achievement 👏 🥝 Meet Kimi K2.5 Open-Source Visual Agentic Intelligence. 🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%) BrowseComp (74.9%) 🔹 Open-source SOTA on Vision and Coding: MMMU Pro (78.5%) VideoMMMU (86.6%) SWE-bench Verified (76.8%) 🔹 Code with"  
[X Link](https://x.com/arena/status/2016984335380001268)  2026-01-29T21:18Z 127K followers, 45.2K engagements


"Top [--] Open Models by Provider - shifts for January [----] in the Text Arena: ✨One new entrant stormed to the top of the board Kimi-K2.5-Thinking from @Kimi_Moonshot takes the #1 spot 💪 Holding Firm Mistral-Large-3 by @mistralAI sticks to #5 @Meituan_LongCat's Longcat-flash-chat holds on to #6 Mimo-v2-flash (non-thinking) by @Xiaomi keeps #7 Minimax-M2.1 by @MiniMax__AI ranks #8 Gemma-3-27b-it by @GoogleDeepMind stays at #9 Intellect-3 by @PrimeIntellect maintains the final slot at #10 🚶 Movers GLM-4.7 from @Zai_org drops to #2 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen moves up from #4"  
[X Link](https://x.com/arena/status/2018727508955574580)  2026-02-03T16:45Z 128.8K followers, [----] engagements


"🌐🚨Search Arena Leaderboard Update Four frontier models have landed on the Search leaderboard and the Top [--] have been disrupted: #1 gemini-3-flash-grounding by @GoogleDeepmind (+6pts over gemini-3-pro-grounding) #5 gpt-5.2-search-non-reasoning by @OpenAI (only non-reasoning in Top 5) #7 claude-opus-4-5-search by @AnthropicAI (best Claude variant in search) #13 claude-sonnet-4-5-search by @AnthropicAI (+3pts over claude-opus-4-1-search) In Search Arena frontier models are evaluated on real-time search queries and citation source quality. Come test them with your hardest queries."  
[X Link](https://x.com/arena/status/2018760874178342975)  2026-02-03T18:57Z 127K followers, 22.8K engagements


"📉✂Image Arena Pareto Frontier: Image Edit Now lets take a look at image editing. Looking at Arena Score versus price per image lets us see which models sit on the Pareto frontier across both efficient and highly complex image editing. Top models on the Pareto frontier for Single-Image-Edit: - @OpenAI: ChatGPTImageHighFidelity - @Bytedance: Seedream4.5 Seedream42K - @GoogleDeepMind: NanoBanana - @bfl_ml: Flux2Klein9B Flux2Dev - @reve: ReveV1.1Fast Check out thread for differences in Multi-Image Edit 👇 📉🖼Image Arena Pareto Frontier Image use cases vary widely. Sometimes you want the highest"  
[X Link](https://x.com/arena/status/2018792314878234704)  2026-02-03T21:02Z 127.9K followers, [----] engagements


"📉✂🔢Image Arena Pareto Frontier: Multi-Image-Edit - @GoogleDeepMind: NanoBananaPro2K NanoBanana - @OpenAI: ChatGPTImageHighFidelity - @Bytedance: Seedream4.5 - @bfl_ml: Flux2Pro Flux2Klein9B Flux2Dev - @PrunaAI: PImageEdit"  
[X Link](https://x.com/arena/status/2018792316782391746)  2026-02-03T21:02Z 128.4K followers, 13.3K engagements


"🚨Claude Opus [---] by @AnthropicAI is in the Arena Available in the Text and Code Arena waiting for your toughest real-world prompts. Test it across both general and agentic tasks. Dont forget to vote well find out how it ranks this week Introducing Claude Opus [---]. Our smartest model got an upgrade. Opus [---] plans more carefully sustains agentic tasks for longer operates reliably in massive codebases and catches its own mistakes. Its also our first Opus-class model with 1M token context in beta. https://t.co/L1iQyRgT9x Introducing Claude Opus [---]. Our smartest model got an upgrade. Opus 4.6"  
[X Link](https://x.com/arena/status/2019473232886214728)  2026-02-05T18:08Z 128.7K followers, [----] engagements


"Claude Opus [---] - first impressions 👀 Arena AI Capabilities Lead @petergostev breaks down the latest from @AnthropicAI on YouTube 🔽 Test it out for yourself and get voting. Scores from real-world use straight from the community coming soon. https://youtu.be/xI3RmeSoMiI https://youtu.be/xI3RmeSoMiI"  
[X Link](https://x.com/arena/status/2019538906132422769)  2026-02-05T22:29Z 128.5K followers, 13.8K engagements


"Check out Claude Opus [---] for yourself in the Code Arena and don't forget to vote: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2019538907319448002)  2026-02-05T22:29Z 128.5K followers, [----] engagements


"How much better is Claude Opus [---] by @AnthropicAI vs. past models We compared Opus [---] to Opus [---] on a set of challenging SVG generations in Code Arena: 🚨BREAKING: Claude Opus [---] by @AnthropicAI is now #1 across Code Text and Expert Arena Opus [---] shows significant gains across the board: - #1 Code Arena: +106 score vs Opus [---] - #1 Text Arena: scoring [----] +10 vs Gemini [--] Pro - #1 Expert Arena: +50 lead Congrats to the https://t.co/bGB9ydFUsp 🚨BREAKING: Claude Opus [---] by @AnthropicAI is now #1 across Code Text and Expert Arena Opus [---] shows significant gains across the board: - #1"  
[X Link](https://x.com/arena/status/2019859455626866766)  2026-02-06T19:43Z 128.8K followers, 58.6K engagements


"Check out Claude Opus [---] for yourself in Code Arena at: http://www.arena.ai/code http://www.arena.ai/code"  
[X Link](https://x.com/arena/status/2019859457325580683)  2026-02-06T19:43Z 127.9K followers, [----] engagements


"BREAKING: Kimi K2.5 Instant by @Kimi_Moonshot is in the Top [--] open models for Vision Text and Code As a non-thinking model Kimi K2.5 Instant delivers strong - in range with proprietary models in the Top 25: - #2 open in Vision #10 overall; on par with gpt-5.1 - #3 open in Text #26 overall; on par with o3 and Qwen3-max-preview - #4 open in Code #10 overall; rivaling gemini-3-flash Congrats to the @Kimi_Moonshot team for pushing the frontier of open models 👏 🥝 Meet Kimi K2.5 Open-Source Visual Agentic Intelligence. 🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%) BrowseComp (74.9%)"  
[X Link](https://x.com/arena/status/2019901514677121413)  2026-02-06T22:30Z 128.8K followers, 15.5K engagements


"Kimi K2.5 Instant is the #3 open model in Text and ranks #26 overall - scoring [----] the same as o3-2025-04-16 and 1pt from Qwen3-max-preview"  
[X Link](https://x.com/arena/status/2019901516761690428)  2026-02-06T22:30Z 128.7K followers, [----] engagements


"Check out Image Arena leaderboard details at: https://arena.ai/leaderboard/text-to-image https://arena.ai/leaderboard/text-to-image"  
[X Link](https://x.com/arena/status/2020184567349665983)  2026-02-07T17:15Z 128.7K followers, [----] engagements


"Check out Grok-Imagine-Image and Grok-Imagine-Image-Pro vs. all the best frontier models at: https://arena.ai/c/newchat-modality=image https://arena.ai/c/newchat-modality=image"  
[X Link](https://x.com/arena/status/2020184568628932885)  2026-02-07T17:15Z 128.7K followers, [----] engagements


"Check out the live Leaderboards for Image Arena here: https://arena.ai/leaderboard/image-edit https://arena.ai/leaderboard/image-edit"  
[X Link](https://x.com/arena/status/2020215935878250791)  2026-02-07T19:19Z 128.9K followers, [----] engagements


"RT @JiachenLi11: The Grok Imagine Image model is we've been sprinting toward these past few months. We've proven that a truly exceptional m"  
[X Link](https://x.com/arena/status/2020234637696745902)  2026-02-07T20:34Z 128.6K followers, [--] engagements


"RT @arena: 🚨BREAKING: Claude Opus [---] by @AnthropicAI is now #1 across Code Text and Expert Arena Opus [---] shows significant gains acros"  
[X Link](https://x.com/arena/status/2020245878720852454)  2026-02-07T21:18Z 128.6K followers, [--] engagements


"RT @elonmusk: Great work by the @Grok Imagine team"  
[X Link](https://x.com/arena/status/2020294991902650578)  2026-02-08T00:33Z 128.6K followers, [----] engagements


"RT @xai: The new image models are now available on Grok Imagine API. Try them at https://docs.x.ai/developers/model-capabilities/images/generation https://docs.x.ai/developers/model-capabilities/images/generation"  
[X Link](https://x.com/arena/status/2020603206473257058)  2026-02-08T20:58Z 128.6K followers, [---] engagements


"Check out Claude Opus [---] for yourself in the Code Arena at: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2020895850315284671)  2026-02-09T16:21Z 128.8K followers, [----] engagements


"Claude Opus [---] thinking and non-thinking are ranked #1 and #2 in the Text Arena. Anthropic now holds [--] of the top [--] Text models"  
[X Link](https://x.com/arena/status/2020956229745639663)  2026-02-09T20:21Z 128.7K followers, [----] engagements


"Check out Claude Opus [---] thinking and non-thinking on the Code Arena leaderboard at: https://arena.ai/leaderboard/code https://arena.ai/leaderboard/code"  
[X Link](https://x.com/arena/status/2020956231603716376)  2026-02-09T20:21Z 128.7K followers, [----] engagements


"Image Arena now includes [--] new prompt Categories to view the leaderboard by: 🛍Product Branding & Commercial Design 🧊3D Imaging & Modeling 🐉Cartoon Anime & Fantasy 🌅Photorealistic & Cinematic Imagery 🎨Art 👤Portraits 📝Text Rendering Read more on our blog for prompt examples: http://arena.ai/blog/image-arena-improvements http://arena.ai/blog/image-arena-improvements"  
[X Link](https://x.com/arena/status/2020977734986629531)  2026-02-09T21:46Z 128.7K followers, [----] engagements


"New Quality Filtering for Image Arena: To improve data quality in the Text-to-Image Arena we filtered the prompt set to focus on cases that reliably deliver quality image generation. After removing 15% of noisy prompts we recomputed the leaderboardyielding more stable higher-confidence rankings. These updates are just the first step toward more granular interpretable evaluation of text-to-image models. Explore your favorite text-to-image models perform across these categories on the Text-to-Image Arena Leaderboard at: https://arena.ai/leaderboard/text-to-image"  
[X Link](https://x.com/arena/status/2020977736886677526)  2026-02-09T21:46Z 128.7K followers, [----] engagements


"Try PDF uploads in Battle and Side by Side at http://arena.ai http://arena.ai"  
[X Link](https://x.com/arena/status/2021300539468939500)  2026-02-10T19:09Z 128.9K followers, [----] engagements


"@Joseph434631433 this one is for you"  
[X Link](https://x.com/arena/status/2021300540630815089)  2026-02-10T19:09Z 128.9K followers, [----] engagements


"Exciting News from Chatbot Arena @GoogleDeepMind's new Gemini [---] Pro (Experimental 0801) has been tested in Arena for the past week gathering over 12K community votes. For the first time Google Gemini has claimed the #1 spot surpassing GPT-4o/Claude-3.5 with an impressive score of [----] () and also achieving #1 on our Vision Leaderboard. Gemini [---] Pro (0801) excels in multi-lingual tasks and delivers robust performance in technical areas like Math Hard Prompts and Coding. Huge congrats to @GoogleDeepMind on this remarkable milestone Gemini (0801) Category Rankings: - Overall: #1 - Math: #1-3"  
[X Link](https://x.com/arena/status/1819048821294547441)  2024-08-01T16:33Z 128.9K followers, 1.3M engagements


"📰More exciting news today: @xai's latest Grok-3 tops the Arena leaderboard 🔥 This is the newest production model grok-3-preview-02-24 With over 3k votes this model is tied for #1 overall and across Hard Prompts Coding Math Creative Writing Instruction Following and Longer Query. Huge congratulations to @xai on this impressive milestone 🙌"  
[X Link](https://x.com/arena/status/1896675400916566357)  2025-03-03T21:33Z 128.9K followers, 5.9M engagements


"The NEW LMArena is officially live 🎉 ✨ New Logo ⚡ Better faster UI/UX for chat and leaderboard 📱 Mobile optimized 💬 Chat history 🧭 Clearer leaderboard navigation 🤖 Many modalities in one place: vision image and more coming soon Try it now at lmarena dot ai (Link in 🧵)"  
[X Link](https://x.com/arena/status/1927400454922580339)  2025-05-27T16:24Z 128.9K followers, 267.7K engagements


"🚨Breaking: New Gemini-2.5-Pro (06-05) takes the #1 spot across all Arenas again 🥇 #1 in Text Vision WebDev 🥇 #1 in Hard Coding Math Creative Multi-turn Instruction Following and Long Queries categories Huge congrats @GoogleDeepMind Gemini [---] Pro - our most intelligent model is getting an update before general availability. ✨ Its even better at: coding 🖥 reasoning 💡 and creative writing ✍ Learn more. 🧵 https://t.co/KBVcO5CCur Gemini [---] Pro - our most intelligent model is getting an update before general availability. ✨ Its even better at: coding 🖥 reasoning 💡 and creative writing ✍"  
[X Link](https://x.com/arena/status/1930658518560133435)  2025-06-05T16:10Z 128.9K followers, 311.6K engagements


"🚨 BIG NEWS: An announcement from our intern Introducing 🎬 Video Arena"  
[X Link](https://x.com/arena/status/1950593176009662698)  2025-07-30T16:23Z 128.9K followers, 151.9K engagements


"GPT-5 is here - and its #1 across the board. 🥇#1 in Text WebDev and Vision Arena 🥇#1 in Hard Prompts Coding Math Creativity Long Queries and more Tested under the codename summit GPT-5 now holds the highest Arena score to date. Huge congrats to @OpenAI on this record-breaking achievement GPT-5 is here. Rolling out to everyone starting today. https://t.co/rOcZ8J2btI https://t.co/dk6zLTe04s GPT-5 is here. Rolling out to everyone starting today. https://t.co/rOcZ8J2btI https://t.co/dk6zLTe04s"  
[X Link](https://x.com/arena/status/1953504958378356941)  2025-08-07T17:14Z 128.9K followers, 757.9K engagements


"🚨 Leaderboard Disrupted Grok-4-fast by @xAI has arrived in the Arena and its shaking things up ⚡ 🏆 #1 on the Search Leaderboard Tested under the codename menlo Grok-4-fast-search just rocketed to the top spot with the community. 💠 Tied for #8 on the Text Leaderboard After debuting as tahoe in pre-release Grok-4-fast is officially in the Top [--] - no small feat in the most competitive Arena particularly for a model in this weight class. 👏 Congrats to the @xAI team on these achievements. See thread for more highlights about Grok-4-fast 🧵 Introducing Grok [--] Fast a multimodal reasoning model"  
[X Link](https://x.com/arena/status/1969185052878914006)  2025-09-19T23:41Z 128.9K followers, 4.6M engagements


"🚀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"  
[X Link](https://x.com/arena/status/1988665193275240616)  2025-11-12T17:48Z 128.9K followers, 326.5K engagements


"🚨 Top [--] Open Models in January: Text Arena Looking back last month here are the rankings by provider for January: 🥇 #1 Kimi-K2.5-Thinking by @Kimi_Moonshot (Modified MIT) 🥈 #2 GLM-4.7 by @Zai_org (MIT) 🥉 #3 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen (Apache 2.0) Compared to December the ranks have shifted with new variants but the top labs have not changed. The top [--] open models all score above [----]. Will we see our first [----] breakthroughs this year See more details around the climbers and movers for January in thread 🧵 https://twitter.com/i/web/status/2018727506850033854"  
[X Link](https://x.com/arena/status/2018727506850033854)  2026-02-03T16:45Z 128.9K followers, 54.5K engagements


"📉🖼Image Arena Pareto Frontier Image use cases vary widely. Sometimes you want the highest quality and sometimes you need something efficient enough to run at scale. Looking at Arena Score versus price per image lets us see which models sit on the Pareto frontier. Top models on the Pareto frontier for Text-to-Image: - @OpenAI: GPTImage1.5HighFidelity GPTImage1Mini - @bfl_ml: Flux2Max Flux2Flex Flux2Pro Flux2Dev - @GoogleDeepMind: NanoBanana - @TencentGlobal: HunyuanImage3.0 - @PrunaAI: PImage https://twitter.com/i/web/status/2018787949840896119"  
[X Link](https://x.com/arena/status/2018787949840896119)  2026-02-03T20:45Z 128.9K followers, 12.1K engagements


"👋Say hello to Max Max is Arenas intelligent router powered by 5+ million real-world community votes. Max routes each prompt to the most capable model with latency in mind. AI models excel at different things (code math speed reasoning). Max orchestrates across model strengths to deliver reliable performance across real-world use cases. Available today in Direct chat https://twitter.com/i/web/status/2019112479943696463 https://twitter.com/i/web/status/2019112479943696463"  
[X Link](https://x.com/arena/status/2019112479943696463)  2026-02-04T18:15Z 128.9K followers, 30K engagements


"🚨New Model Alert Seed [---] by Bytedance is the Text Vision & Code Arena Bring your toughest prompts to Seed [---] and see how it stacks up. Remember your votes drive the leaderboards"  
[X Link](https://x.com/arena/status/2019200450889957486)  2026-02-05T00:04Z 128.9K followers, 11.6K engagements


"📉 Video Arena Pareto Frontier Its not just about being the best model. Its also about being the best at the right price point. By comparing Arena Score for video models against price per second we can identify the Pareto frontier: the best-performing model available at each price point. Top models on the Pareto frontier for Image-to-Video: - @xAI: Grok Imagine Video (720p and 480p) - @BytedanceTalk: Seedance v1.5 Pro - @Hailuo_AI : Hailuo [--] Standard https://twitter.com/i/web/status/2019427062071877717 https://twitter.com/i/web/status/2019427062071877717"  
[X Link](https://x.com/arena/status/2019427062071877717)  2026-02-05T15:05Z 128.9K followers, 12.5K engagements


"Have you met Max Live on Arena. Powered by 5M+ real-world community votes Max intelligently routes each prompt to the most capable model with latency in mind. You get more reliable results across real use cases without having to choose. Heres a quick clip with Arena researcher Derry 👇 Catch the full walkthrough on our YouTube (link in 🧵). https://twitter.com/i/web/status/2019460554436620689 https://twitter.com/i/web/status/2019460554436620689"  
[X Link](https://x.com/arena/status/2019460554436620689)  2026-02-05T17:18Z 128.9K followers, [----] engagements


"🚨BREAKING: Claude Opus [---] by @AnthropicAI is now #1 across Code Text and Expert Arena Opus [---] shows significant gains across the board: - #1 Code Arena: +106 score vs Opus [---] - #1 Text Arena: scoring [----] +10 vs Gemini [--] Pro - #1 Expert Arena: +50 lead Congrats to the @AnthropicAI team on the incredible milestone The frontier just moved. Introducing Claude Opus [---]. Our smartest model got an upgrade. Opus [---] plans more carefully sustains agentic tasks for longer operates reliably in massive codebases and catches its own mistakes. Its also our first Opus-class model with 1M token context"  
[X Link](https://x.com/arena/status/2019842691442569566)  2026-02-06T18:36Z 128.9K followers, 212.2K engagements


"🖼 Updates to the Image Arena Leaderboard Text-to-image models have advanced quickly and so have use cases. After analyzing 4M+ user prompts (from fantasy art to logos and posters) its clear that a single leaderboard is no longer enough to capture real-world use. Were updating the Text-to-Image Arena with: Prompt Categories: category-specific leaderboards for clearer domain-level performance Quality Filtering: reducing noisy or underspecified prompts for more reliable rankings Learn more about the prompt categories in thread 👇 https://twitter.com/i/web/status/2020977733308985350"  
[X Link](https://x.com/arena/status/2020977733308985350)  2026-02-09T21:46Z 128.9K followers, 21.8K engagements


"Read more about Arenas Academic Partnerships Program on our blog: https://arena.ai/blog/academic-partnerships-program https://arena.ai/blog/academic-partnerships-program"  
[X Link](https://x.com/arena/status/2021268437683654848)  2026-02-10T17:02Z 128.9K followers, [----] engagements


"📄We just launched PDF uploads in Arena. Upload PDFs with your prompts to add richer context and test models on document reasoning bringing evaluations closer to real-world use. Ask questions directly against documents Digest complex technical content in minutes Extract summaries and key takeaways instantly Try it across [--] models today - well be adding more over time. Leaderboard coming soon. Start uploading comparing and voting https://twitter.com/i/web/status/2021300537711526113 https://twitter.com/i/web/status/2021300537711526113"  
[X Link](https://x.com/arena/status/2021300537711526113)  2026-02-10T19:09Z 128.9K followers, 21.1K engagements


"Arena isnt just one leaderboard. There are leaderboards by modality category and even ones filtered by Expert prompts and Occupational fields. ICYMI also separate Text Coding vs. agentic Code Arena views. Were adding new filters and categories all the time like our latest Text-to-Image categories. Learn how to find the best model for your real-world use casse in our video with AI capabilities lead @petergostev on our YouTube channel in thread 👇 🖼 Updates to the Image Arena Leaderboard Text-to-image models have advanced quickly and so have use cases. After analyzing 4M+ user prompts (from"  
[X Link](https://x.com/arena/status/2021340893702439174)  2026-02-10T21:49Z 128.9K followers, [----] engagements


"Learn more about all Arena leaderboards on our Youtube: https://www.youtube.com/watchv=bWamcBztN0w https://www.youtube.com/watchv=bWamcBztN0w"  
[X Link](https://x.com/arena/status/2021340895711461485)  2026-02-10T21:49Z 128.9K followers, [----] engagements


"Create production ready multi-file react apps with the top frontier AI models. Bring your toughest agentic web dev coding tasks to: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2021643290077204715)  2026-02-11T17:51Z 128.9K followers, [----] engagements


"Start building your next app in the Code Arena at: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2021647297856368803)  2026-02-11T18:07Z 128.9K followers, [----] engagements


"Walkthrough multi-file react apps with Code Arena creator @aryanvichare10 on Youtube: https://youtu.be/lAFsaT5oi8g https://youtu.be/lAFsaT5oi8g"  
[X Link](https://x.com/arena/status/2021647298959462531)  2026-02-11T18:07Z 128.9K followers, [----] engagements


"Check at the Text leaderboard details at: https://arena.ai/leaderboard/text https://arena.ai/leaderboard/text"  
[X Link](https://x.com/arena/status/2021725352725504463)  2026-02-11T23:17Z 128.9K followers, [----] engagements


"Check at the Code leaderboard details at: https://arena.ai/leaderboard/code https://arena.ai/leaderboard/code"  
[X Link](https://x.com/arena/status/2021996282953535834)  2026-02-12T17:14Z 129K followers, [----] engagements


"RT @iamwaynechi: @infwinston and @ml_angelopoulos were fantastic to work with and @CopilotArena would not have been possible without them"  
[X Link](https://x.com/arena/status/2022058285235609832)  2026-02-12T21:20Z 128.9K followers, [--] engagements


"🚨Text Leaderboard Update @xAIs Grok [---] (thinking) and Grok [---] have scaled new heights in the most competitive Text Arena: 🔹Grok [---] (thinking) lands at #1 with a score of [----] 🔹Grok [---] follows at #2 with a score of [----] On the Arena Expert leaderboard: 🔸Grok [---] (thinking) also ranks at #1 with a score of [----] 🔸Grok [---] ranks at #19 with score of [----] This is a 40+ point improvement since Grok [--] fast which landed in the Arena just two months prior. Congrats to the @xAI team for this incredible milestone 👏 Introducing Grok [---] a frontier model that sets a new standard for"  
[X Link](https://x.com/arena/status/1990530978943787291)  2025-11-17T21:22Z 129K followers, 5.2M engagements


"🚨BIG NEWS: 🎬 Video Arena is now live on the web Test out Veo [---] Sora [--] Seedance v1.5 Pro Kling [---] Pro Wan [---] & more. What started last summer as a small Discord bot experiment has grown into a rigorous way to measure and understand how frontier video models perform with real-world use. Thank you to our wonderful community for all the feedback Today were opening up access by making it available on the web. 🎥 Generate videos with [--] different frontier AI models and compare them head-to-head. 📊 Vote for the best output to power the leaderboards."  
[X Link](https://x.com/arena/status/2014035528979747135)  2026-01-21T18:01Z 129K followers, 61.5K engagements


"LMArena is now Arena. A name that takes us back to our roots with a powerful mission: to measure and advance the frontier of AI for real-world use. We have grown from a small PhD research project to a platform powered by a global community of millions. This rebrand has been shaped by the people who use it. 👇 Take a look inside the rebrand"  
[X Link](https://x.com/arena/status/2016577708831232140)  2026-01-28T18:22Z 129K followers, 91.2K engagements


"🚨BREAKING: @xAIs first model in Video Arena debuts in the top [--] Grok-Imagine-Video ranks #3 on the Image-to-Video Arena and #4 on the Text-to-Video Arena. It is close to the top-ranked @GoogleDeepMind Veo [---] and @OpenAI Sora [--] Pro models. Grok-Imagine-Video offers: - Text-to-video and image-to-video capabilities - Native audio generation - Up to 15-seconds video duration Congrats to @xAI on this strong launch Understanding requires imagining. Grok Imagine lets you bring whats in your brain to life and now its available via the worlds fastest and most powerful video API:"  
[X Link](https://x.com/arena/status/2016748418635616440)  2026-01-29T05:41Z 129K followers, 112.5K engagements


"🚨BREAKING: Kimi K2.5 by @Kimi_Moonshot is now the #1 open model in Code Arena In Code Arenas agentic coding evaluations Kimi K2.5 is now: - #1 open model surpassing GLM-4.7 - #5 overall on par with top proprietary models like Gemini-3-Flash - The only open model in the top [--] 🏆Kimi K2.5 is the best open model across Text Vision and Code Arena. Huge congrats to the @Kimi_Moonshot team for continuing to push the frontier of open models 👏 🥝 Meet Kimi K2.5 Open-Source Visual Agentic Intelligence. 🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%) BrowseComp (74.9%) 🔹 Open-source SOTA"  
[X Link](https://x.com/arena/status/2018355347485069800)  2026-02-02T16:06Z 129K followers, 193.6K engagements


"BREAKING: @xAIs Grok-Imagine-Video now #1 in Video Arena For the first time Grok-Imagine-Video-720p takes the top spot on the Image-to-Video leaderboard overtaking Googles Veo [---] while being 5x cheaper. Its 480p version released a few days ago ranks #4. Huge congrats to @xAI team and @elonmusk on this incredible milestone Introducing Grok Imagine [---] our biggest leap yet. [---] unlocks 10-second videos 720p resolution and dramatically better audio. Imagine has generated [-----] billion videos in the last [--] days alone. Try it now: https://t.co/zGhs9czkC5 https://t.co/7FPxm7H059 Introducing Grok"  
[X Link](https://x.com/anyuser/status/2019204821551837665)  2026-02-05T00:21Z 129K followers, 1.8M engagements


"Latest image models from @xAI Grok-Imagine-Image and Pro debut top [--] in the Image Arena Text-to-Image: #4 Grok-Imagine-Image; scoring [----] surpassing Flux-2-max and Nano-banana #6 Grok-Imagine-Image-Pro Image-Edit: #5 Grok-Imagine-Image-Pro; scoring [----] overtaking Seedream-4.5 #6 Grok-Imagine-Image With this launch @xAI is now a top-3 Image AI provider alongside @GoogleDeepMind and @OpenAI. Congrats to the @xAI team on the impressive releases https://twitter.com/i/web/status/2020184563855815135 https://twitter.com/i/web/status/2020184563855815135"  
[X Link](https://x.com/arena/status/2020184563855815135)  2026-02-07T17:15Z 129K followers, 98.8K engagements


"When looking specifically at Text-to-Image the Pareto frontier also expands with the introduction of @xAIs latest Grok-Imagine-Image model. Top models for Text-to-Image: - @OpenAI: GPT-Image-1.5-high-fidelity - @xAI: Grok Imagine Image - @bfl_ml: Flux-2-Dev - @OpenAI: GPT-Image-1-Mini - @PrunaAI: P-Image https://twitter.com/i/web/status/2020215933898526791 https://twitter.com/i/web/status/2020215933898526791"  
[X Link](https://x.com/arena/status/2020215933898526791)  2026-02-07T19:19Z 129K followers, 13.5K engagements


"Weve challenged Claude Opus [---] by @AnthropicAI with our hardest 3D prompts it did not disappoint. Introducing Claude Opus [---]. Our smartest model got an upgrade. Opus [---] plans more carefully sustains agentic tasks for longer operates reliably in massive codebases and catches its own mistakes. Its also our first Opus-class model with 1M token context in beta. https://t.co/L1iQyRgT9x Introducing Claude Opus [---]. Our smartest model got an upgrade. Opus [---] plans more carefully sustains agentic tasks for longer operates reliably in massive codebases and catches its own mistakes. Its also our"  
[X Link](https://x.com/arena/status/2020895848385970275)  2026-02-09T16:21Z 129K followers, 99.6K engagements


"High-res 1080p variants for Veo [---] by @GoogleDeepMind now rank #1 and #2 in Video Arena In Text-to-Video the 1080p versions top the chart #1 veo-3.1-audio-1080p #2 veo-3.1-fast-audio-1080p In Image-to-Video 1080p variants make the top [--] #2 veo-3.1-audio-1080p #5 veo-3.1-fast-audio-1080p Its exciting to see new variants push video generation forward for the community. https://twitter.com/i/web/status/2021387439827538427 https://twitter.com/i/web/status/2021387439827538427"  
[X Link](https://x.com/arena/status/2021387439827538427)  2026-02-11T00:54Z 129K followers, 10.6K engagements


"In Image-to-Video 1080p variants make the top 5: #2 veo-3.1-audio-1080p #5 veo-3.1-fast-audio-1080p"  
[X Link](https://x.com/arena/status/2021387442314789139)  2026-02-11T00:54Z 129K followers, [----] engagements


"Check out all the best frontier video AI models at: http://arena.ai/video http://arena.ai/video"  
[X Link](https://x.com/arena/status/2021387443862372858)  2026-02-11T00:54Z 129K followers, [----] engagements


"A new open-source model has entered the Arena. Come check out @Zai_orgs latest GLM-5 in Text and Code. Test out its coding chops in Text and its agentic coding capabilities in Code. Battle with the top frontier models and dont forget to vote - scores coming soon. Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5 it scales from 355B params (32B active) to 744B (40B active) with pre-training data growing from 23T to 28.5T tokens. https://t.co/uGYQUjIbbs Introducing GLM-5: From Vibe Coding"  
[X Link](https://x.com/arena/status/2021643288273727786)  2026-02-11T17:51Z 129K followers, 16.1K engagements


"Multi-file apps are now live in Code Arena Since launching Code Arena in November to evaluate frontier AI models on real-world agentic coding tasks weve received a lot of feedback asking to adapt more complex workflows. With multi-file apps you can now build and compare production-ready projects making it easier to evaluate how top frontier AI models perform on your actual use cases. https://twitter.com/i/web/status/2021647296526745676 https://twitter.com/i/web/status/2021647296526745676"  
[X Link](https://x.com/arena/status/2021647296526745676)  2026-02-11T18:07Z 129K followers, [----] engagements


"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 @Zai_org 's GLM-5 in Code Arena coming soon. Test out GLM-5 for yourself and get voting. GLM-5 from @Zai_org just climbed to #1 among open models in Text Arena #1 open model on par with claude-sonnet-4.5 & gpt-5.1-high #11 overall; scoring [----] +11pts over GLM-4.7 Test it out in the Code Arena and keep voting well see how GLM-5 performs for agentic coding https://t.co/MajenrS0Qz GLM-5 from @Zai_org just"  
[X Link](https://x.com/arena/status/2021732547349344690)  2026-02-11T23:46Z 129K followers, 114.5K engagements


"Test out SVG creations sites and multi-file apps for yourself with GLM-5 in the Code Arena at: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2021732549211656561)  2026-02-11T23:46Z 129K followers, [----] engagements


"🚨Busy week for new models in the Arena: MiniMax M2.5 by @MiniMax_AI is now available in the Text and Code Arena. Bring your toughest prompts and see how it stacks up against the latest models in real-world use. In Battle mode your votes power the leaderboards. Learn more about the latest models in the Arena in thread 👇 Introducing M2.5 an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%) search (BrowseComp 76.3%) agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution 37% faster at complex"  
[X Link](https://x.com/arena/status/2021987555655422257)  2026-02-12T16:39Z 129K followers, [----] engagements


"With the competition heating up this week check out first impressions on MiniMax M2.5 by @MiniMax_AI and GLM-5 by @Zai_org with our AI capabilities expert @petergostev on YouTube: https://youtu.be/TbK2ngEJUmg https://youtu.be/TbK2ngEJUmg"  
[X Link](https://x.com/arena/status/2021987558314631467)  2026-02-12T16:39Z 129K followers, [----] engagements


"Test out MiniMax M2.5's agentic capabilities for yourself in the Code Arena at: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2021987559908524354)  2026-02-12T16:39Z 129K followers, [----] engagements


"🚨New model in the Arena: @OpenAI's GPT-5.2 is now available in the Text and Vision Arena. Check it out in Battle mode with your most creative and toughest prompts to see how it stacks up to real-world use. Your votes drive the leaderboards scores coming soon. GPT-5.2 is now rolling out to everyone. https://t.co/nfubPwnIIw GPT-5.2 is now rolling out to everyone. https://t.co/nfubPwnIIw"  
[X Link](https://x.com/arena/status/2022376662126748002)  2026-02-13T18:25Z 129K followers, 40.6K engagements


"Learn more about all the various Arena leaderboards on our YouTube: https://www.youtube.com/watchv=bWamcBztN0w https://www.youtube.com/watchv=bWamcBztN0w"  
[X Link](https://x.com/arena/status/2022376665557668262)  2026-02-13T18:25Z 129K followers, [----] engagements


"Test out GPT-5.2 vs all the best frontier AI at: http://arena.ai http://arena.ai"  
[X Link](https://x.com/arena/status/2022376667256361144)  2026-02-13T18:25Z 129K followers, [----] engagements


"@OpenAI To be specific this is an updated version of GPT-5.2 with the API name: "gpt-5.2-chat-latest" See OpenAI changelog here: https://developers.openai.com/api/docs/changelog https://developers.openai.com/api/docs/changelog"  
[X Link](https://x.com/arena/status/2022449080727986442)  2026-02-13T23:13Z 129K followers, [----] engagements


"Kling-3.0 is in the Video Arena. Come test out @Kling_AI's latest model in Text-to-Video and Image-to-Video. In Battle Mode enter one prompt and receive two anonymous model responses side by side. Vote for the better response to help shape the leaderboard. Well soon see how it performs against the top models. 🚀 Introducing the Kling [---] Model: Everyone a Director. Its Time. An all-in-one creative engine that enables truly native multimodal creation. - Superb Consistency: Your characters and elements always locked in. - Flexible Video Production: Create 15s clips with precise"  
[X Link](https://x.com/arena/status/2022503816126673129)  2026-02-14T02:51Z 129K followers, [----] engagements


"Come test out Kling-3.0 vs. all the top frontier AI at: http://arena.ai/video http://arena.ai/video"  
[X Link](https://x.com/arena/status/2022503818622308529)  2026-02-14T02:51Z 129K followers, [----] engagements


"Valentines Day but for model evals 💘 We curated a set of Valentines Day SVG prompts to compare the latest frontier model capabilities for fun. SVGs are a fast way to surface real differences quickly. We can look at: Instruction following Coordination across multiple parts of the code Stability across generations Let us know what you think 👇 https://twitter.com/i/web/status/2022713021081227558 https://twitter.com/i/web/status/2022713021081227558"  
[X Link](https://x.com/arena/status/2022713021081227558)  2026-02-14T16:42Z 129K followers, 12.7K engagements


"Leave your mark on the AI leaderboards by testing and voting across the top frontier AI models with your real world agentic tasks at: http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2022713023975309390)  2026-02-14T16:42Z 129K followers, [----] engagements


"Turn any image into a production-ready website with Code Arena. Code Arena lets you generate real multi-file React apps and sites. You can download the codebase or share a live URL instantly. Its built to test and compare frontier models on real-world development tasks. Watch the latest walkthrough in thread 👇 https://twitter.com/i/web/status/2022734108401766448 https://twitter.com/i/web/status/2022734108401766448"  
[X Link](https://x.com/arena/status/2022734108401766448)  2026-02-14T18:06Z 129K followers, [----] engagements


"See how an image becomes a fully functional site in minutes on Code Arena with @aryanvichare10. Don't forget to subscribe to Arena on YouTube so you don't miss out on the latest frontier AI news and product updates: https://www.youtube.com/watchv=iA2UYigWIIY https://www.youtube.com/watchv=iA2UYigWIIY"  
[X Link](https://x.com/arena/status/2022734109395886172)  2026-02-14T18:06Z 129K followers, [----] engagements


"Try uploading an image for yourself in the Code Arena and share your creations via direct URL with us in the comments. http://arena.ai/code http://arena.ai/code"  
[X Link](https://x.com/arena/status/2022734111119675533)  2026-02-14T18:06Z 129K followers, [----] engagements


"❤🔥WebDev Arena Update: Exciting new entries - #2: @deepseek_ai DeepSeek-R1 - #4: New Gemini-2.0-Flash-Thinking DeepSeek-R1 jumps to #2 with only [--] pts gap to Claude [---] Sonnet showing strong capability in real-world coding tasks. Huge congrats to @deepseek_ai again Check out the stats below👇 Breaking News: DeepSeek-R1 surges to the top-3 in Arena🐳 Now ranked #3 Overall matching the top reasoning model o1 while being 20x cheaper and open-weight Highlights: - #1 in technical domains: Hard Prompts Coding Math - Joint #1 under Style Control - MIT-licensed A https://t.co/gwpgD4hmYI Breaking"  
[X Link](https://x.com/arena/status/1882875989610594542)  2025-01-24T19:39Z 128.8K followers, 115.4K engagements


"🚨 🎬 Video Arena Disrupted @Openai's Sora [--] and Sora [--] Pro have landed on the Text-to-Video leaderboard. 🏆 Sora [--] Pro is the first to tie rank with Veo [--] variants for #1. 🥉 Sora [--] comes in at #3 pushing the non-audio variants of Veo [--] into 5th Video models with audio are arriving fast and Sora [--] stands out for its synchronized sound. Competition in the Video Arena is heating up 🔥 ⚔ Sora [--] is here. https://t.co/hy95wDM5nB Sora [--] is here. https://t.co/hy95wDM5nB"  
[X Link](https://x.com/arena/status/1978149396996051007)  2025-10-14T17:22Z 128.8K followers, 77.7K engagements


"RT @hexiang: Imagine-Image is at the Pareto front: Better Faster & Cost efficient🚀 And we will be even better in weeks🫡🫡 (Kudos to the"  
[X Link](https://x.com/arena/status/2020220094983577758)  2026-02-07T19:36Z 128.6K followers, [--] engagements


"🚨🍌Breaking News: Gemini-2.5-Flash-Image-Preview (nano-banana) by @GoogleDeepMind now ranks #1 in Image Edit Arena. In just two weeks: 🟡nano-banana has driven over [--] million community votes in the Arena 🟡Record-breaking 2.5M+ votes casted for this model alone 🟡It has achieved the largest Elo score lead in Arena history (a monster [---] point lead) Huge congrats to @GoogleDeepMind Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds you can now natively"  
[X Link](https://x.com/arena/status/1960343469370884462)  2025-08-26T14:07Z 129K followers, 557.4K engagements


"Chatbot Arena is coming to ICML2024 Come chat with us at 11:30am on Wed 7/24 (@ Hall C 4-9 #709) and hear about: 📊The latest Arena update 🤖How we rank the best models 🔍How we analyze data & its distribution And more below (thread 1/5)"  
[X Link](https://x.com/anyuser/status/1815682965147443666)  2024-07-23T09:38Z 128.9K followers, 26.1K engagements


"Does style matter over substance in Arena Can models "game" human preference through lengthy and well-formatted responses Today we're launching style control in our regression model for Chatbot Arena our first step in separating the impact of style from substance in rankings. Highlights: - GPT-4o-mini Grok-2-mini drop below most frontier models when style is controlled - Claude [---] Sonnet Opus and Llama-3.1-405B rise significantly - In Hard Prompts Claude [---] Sonnet ties for #1 with ChatGPT-4o-latest. Llama-405B climbs to joint #3. More analysis in the thread below👇"  
[X Link](https://x.com/arena/status/1829216988021043645)  2024-08-29T17:58Z 128.9K followers, 234.2K engagements


"BREAKING News: @OpenAI's GPT-4.5 now tops the Arena leaderboard With over 3k votes GPT-4.5 landed #1 across ALL categories and singularly #1 under Style Control / Multi-Turn 🥇 Huge congratulations to @OpenAI on this impressive milestone 🙌 View below for more insights on how GPT-4.5 performed"  
[X Link](https://x.com/anyuser/status/1896590146465579105)  2025-03-03T15:55Z 128.9K followers, 548.9K engagements


"Breaking: new @OpenAI models shake up the Arena leaderboard🔥 Highlights: - o3 #2 overall ties Gemini-2.5-Pro at #1 in Style Control Math Coding and Hard Prompts - o4-mini breaks into top [--] and claims #1 in Math surpassing o1 () - GPT-4.1 ranks top-5 in Hard Prompts Math and Style Control Huge congrats to @OpenAI on the impressive releases More analysis below 🧵"  
[X Link](https://x.com/arena/status/1915078057452573142)  2025-04-23T16:19Z 128.9K followers, 495.8K engagements


"Earlier this month we launched the Image Edit Arena. Today the Image Edit Leaderboard 🏆 goes LIVE powered by more models and all your community votes. 🏆 In 1st place: GPT-Image-1 by @OpenAI 💠 2nd-4th: Flux [--] Kontext Max Pro & Dev by @bfl_ml 💠 5th: Gemini [---] Flash Preview by @GoogleDeepMind Image Editing just got real on LMArena 🖼✨ Introducing Image Edit Arena: where AI editing models go head-to-head on your images. Upload edit vote. It's that simple. Who edits it best You decide🫵 Learn how it works in thread 🧵 https://t.co/BboKK4IRar Image Editing just got real on LMArena 🖼✨"  
[X Link](https://x.com/anyuser/status/1940795298449924220)  2025-07-03T15:30Z 128.9K followers, 33.8K engagements


"🧑🔬 Research Update: Today we are releasing a new dataset with over 140k conversations from the text arena collected between April 17th and July 25th [----]. See thread to dig into it We're pairing the data release with a deep dive into how model performance and evaluation dynamics have evolved over time. Lets look at real-world trends new features and fresh prompts. Whats covered in the latest analysis: - Overview of the released dataset - Language & topic breakdowns - Rating changes: How Arena scores shift over time And more 🧵"  
[X Link](https://x.com/anyuser/status/1950952994557878578)  2025-07-31T16:13Z 128.9K followers, 31.6K engagements


"GPT-5 dominates the Text Arena ranking #1 in every major category: 🧠 Hard Prompts 💻 Coding ➗ Math 🎨 Creative Writing 📝 Long Queries and more"  
[X Link](https://x.com/arena/status/1953504966465008094)  2025-08-07T17:14Z 128.9K followers, 81K engagements


"🚨 Leaderboard shakeup in the top slot Claude Sonnet [---] now tied for #1 in the Text Arena matching Claude Opus [---] 🏆 Quick reminder: the Arena rankings are powered by tens of thousands of real human votes which have put @AnthropicAI's Claude Sonnet [---] joins the very top tier of models like Gemini [---] Pro Claude Opus [---] and GPT-5. Sonnet packs a punch 🥊 across top categories more details in thread 🧵 Introducing Claude Sonnet 4.5the best coding model in the world. It's the strongest model for building complex agents. It's the best model at using computers. And it shows substantial gains"  
[X Link](https://x.com/arena/status/1973828836510085385)  2025-10-02T19:14Z 128.9K followers, 87.2K engagements


"🚀 Introducing Arena Expert: a new LMArena evaluation framework to identify the toughest most expert-level prompts from real users powering a new Expert leaderboard. We also introduce Occupational Categories that underlie eight new leaderboards: 💻 Software & IT Services ✍ Writing Literature & Language 🔬 Life Physical & Social Science 🎭 Entertainment Sports & Media 📈 Business Management & Financial Ops 🧮 Mathematical ⚖ Legal & Government 🩺 Medicine & Healthcare Explore how models perform across fields in thread 🧵 👇"  
[X Link](https://x.com/arena/status/1986153162802368555)  2025-11-05T19:26Z 128.9K followers, 160.8K engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing