[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] #  @arena lmarena.ai lmarena.ai posts on X about ai, 6969, lmarenaai, agentic the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours. ### Engagements: XXXXXX [#](/creator/twitter::1641378826537295874/interactions)  - X Week XXXXXXX -XX% - X Month XXXXXXXXX +736% - X Months XXXXXXXXXX -XX% - X Year XXXXXXXXXX +70% ### Mentions: XX [#](/creator/twitter::1641378826537295874/posts_active)  - X Week XX -XX% - X Month XXX +140% - X Months XXX +84% - X Year XXX +234% ### Followers: XXXXXXX [#](/creator/twitter::1641378826537295874/followers)  - X Week XXXXXXX +2.10% - X Month XXXXXXX +16% - X Months XXXXXXX +39% - X Year XXXXXXX +90% ### CreatorRank: XXXXXXX [#](/creator/twitter::1641378826537295874/influencer_rank)  ### Social Influence **Social category influence** [technology brands](/list/technology-brands) XXXX% **Social topic influence** [ai](/topic/ai) #4682, [6969](/topic/6969) #545, [lmarenaai](/topic/lmarenaai) #1, [agentic](/topic/agentic) #260, [categories](/topic/categories) #123, [banana](/topic/banana) #1410, [nano banana](/topic/nano-banana) #362, [open ai](/topic/open-ai) #1989, [the world](/topic/the-world) 2.9%, [major](/topic/major) #190 **Top accounts mentioned or mentioned by** [@googledeepmind](/creator/undefined) [@grichm77](/creator/undefined) [@zaiorg](/creator/undefined) [@alibabaqwen](/creator/undefined) [@xai](/creator/undefined) [@openai](/creator/undefined) [@googledeepminds](/creator/undefined) [@anthropicai](/creator/undefined) [@deepseekai](/creator/undefined) [@kimimoonshot](/creator/undefined) [@mistralai](/creator/undefined) [@grok](/creator/undefined) [@klingai](/creator/undefined) [@erniefordevs](/creator/undefined) [@elonmusk](/creator/undefined) [@henkpoley](/creator/undefined) [@dhtikna](/creator/undefined) [@achille610](/creator/undefined) [@50hidalgo47](/creator/undefined) [@saifmalik252](/creator/undefined) ### Top Social Posts Top posts by engagements in the last XX hours "🚨 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 XX - 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 🧵" [X Link](https://x.com/arena/status/1969185052878914006) 2025-09-19T23:41Z 113.2K followers, 4.6M engagements "🖼🚨Image Leaderboard Update: The community has been busy comparing and voting on models over the weekend @bfl_mls FLUX.2 Pro and FLUX.2 Flex have landed on the Image leaderboards. Congrats to the @bfl_ml team 👏 Text-to-Image: 🔹FLUX.2 Flex ranks #2 🔹FLUX.2 Pro ranks #5 Image Edit: 🔹FLUX.2 Pro ranks #6 🔹FLUX.2 Flex ranks #7" [X Link](https://x.com/arena/status/1995620748002820130) 2025-12-01T22:27Z 113.2K followers, 24.7K engagements "Gemini-3-pro-image-preview-2k (Nano Banana Pro) has claimed the #1 spot on the Text-to-Image Arena surpassing previous scores set by the Nano Banana variants. View the full leaderboard update here:" [X Link](https://x.com/arena/status/1995989154396770694) 2025-12-02T22:51Z 113.2K followers, 2073 engagements "🌐 Search Leaderboard Update Two new contenders have arrived on the Search leaderboard: Gemini X Pro Grounding (@GoogleDeepMind) and GPT-5.1 (@openai). Current standings: 🥇 #1 gemini-3-pro-grounding 🥈 #2 gpt-5.1-search With a thin 9-point gap between both models the standings may shift quickly as more votes come in. Be sure to vote and stay tuned to see if these rankings hold This is shaping up to be one of the closest races on the leaderboard" [X Link](https://x.com/arena/status/1996348686063083729) 2025-12-03T22:39Z 113.2K followers, 21.8K engagements "👇We want to know what you think. Put it to the test with your toughest prompts and lets see how it ranks:" [X Link](https://x.com/arena/status/1996396397764243893) 2025-12-04T01:49Z 113.2K followers, 4029 engagements "🚨BREAKING: @GoogleDeepMinds Gemini-3-Pro is now #1 across all major Arena leaderboards 🥇#1 in Text Vision and WebDev - surpassing Grok-4.1 Claude-4.5 and GPT-5 🥇#1 in Coding Math Creative Writing Long Queries and nearly all occupational leaderboards. Massive gains over Gemini-2.5: 🔸WebDev in Code Arena: 1487 (+280 pts vs 2.5) 🔸Text: 1501 (+50 pts) 🔸Vision: 1328 (+70 pts) 🔸Arena Expert: Top-3 (just X pts behind #1) Huge congrats to the @GoogleDeepMind team on this breakthrough 👏" [X Link](https://x.com/arena/status/1990813759938703570) 2025-11-18T16:06Z 113.2K followers, 475.9K engagements "🚨🎬 New Video Model update Kling Video XXX is ready in the Video Arena Created by @Kling_ai this is their first model with native audio. Kling Video XXX generates speech sound effects and ambient audio directly in sync with the visuals producing a complete video+audio output in a single step. Hang out with the Arena community and test it with your toughest prompts" [X Link](https://x.com/arena/status/1996744741564961206) 2025-12-05T00:53Z 113.2K followers, 10.5K engagements "🚨BREAKING: New Leaderboard Updates Claude-Opus-4.5 and Opus-4.5 (thinking-32k) just landed on Code Arena (WebDev) and Text Arena leaderboards and Opus-4.5 instantly took #1 in WebDev leaderboard surpassing Gemini X Pro WebDev leaderboard (powered by Code Arena) 🥇#1 for Claude-Opus-4.5 (thinking-32k) 🥈#2 for Claude-Opus-4.5 Expert Leaderboard 🥇#1 for Claude-Opus-4.5 Text Leaderboard - #3 for Claude-Opus-4.5 - #6 for Claude-Opus-4.5 (thinking-32k) Huge congrats to the @AnthropicAI team for such incredible milestone Learn more in the thread on how it performs in key categories and on the" [X Link](https://x.com/arena/status/1993750702179676650) 2025-11-26T18:36Z 113.2K followers, 287.2K engagements "🚨🖼 Image Leaderboard Update Seedream XXX by Bytedance has officially entered the Arena on both the Image Edit and Text-to-Image leaderboards. Here is where it landed: 🔹 #3 on Image Edit (score: 1338) 🔹 #7 on Text-to-Image (score: 1146) This update delivers a 27-pt increase over Seedream-4-2k and a 62-point gain over Seedream-3. This release raises the stakes on the Image Edit leaderboard outperforming Gemini XXX Flash Image (Nano Banana) and landing behind new top variants Nano Banana Pro and its 2k resolution which rank #2 and #1 respectively. Congrats to Bytedance on a strong showing 👏" [X Link](https://x.com/arena/status/1996641968005566876) 2025-12-04T18:05Z 113K followers, 13K engagements "🚨 New Model in the Code Arena GPT-5.1-Codex Max by @OpenAI is ready for you in the Code Arena. Bring your most toughest creative prompts and we'll see how it stacks up against current leaders: Claude Opus XXX Thinking by @anthropicAI and Gemini X Pro by @GoogleDeepMind" [X Link](https://x.com/arena/status/1996692943030354085) 2025-12-04T21:27Z 113.2K followers, 24.3K engagements "Remember your votes drive the leaderboards. Test GPT-5.1 Codex Max in the new Code Arena. 🧑💻 Code Arena is 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:" [X Link](https://x.com/arena/status/1996692945869938934) 2025-12-04T21:27Z 113.2K followers, 3711 engagements "🚨Top XX Open Models by Provider for November The open model race continues with new models entering the Text Arena. Confidence intervals are getting tighter and the competition is heating up Here are the November Top 3: 🥇 #1 Kimi-K2-Thinking-Turbo by @Kimi_Moonshot (Modified MIT) 🥈 #2 GLM-4.6 from @Zai_org (MIT) 🥉 #3 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen (Apache 2.0) Recent releases of new proprietary models have reshuffled the universal rankings lowering the positions of some long-standing open models. Even so every open model still holds a strong place within the Top XXX on the" [X Link](https://x.com/arena/status/1995534475070243043) 2025-12-01T16:44Z 112.9K followers, 25.3K engagements "Top XX Open Models by Provider shifts for November: ✨ New Entrants 🔹 Kimi-K2-Thinking-Turbo by @Kimi_Moonshot zooms to the top at #1 🚀 💪 Holding Firm 🔹 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen maintains at #3 🔹 Longcat-flash-chat by @Meituan_LongCat holds steady mid-pack at #5 🔹 MiniMax M1 by @minimax_ai stays at #6 🔹 Gemma-3-27b-it by @googledeepmind maintains at #7 🔹 Mistral-Small-2506 by @MistralAI hanging in at #8 🚶 Movers 🔹 Deepseek-V3.2-Exp-Thinking by @Deepseek_AI drops to #4 🔹 GLM-4.6 by @Zai_org drops to #2 🔹 GPT-oss-120b by @openAI overtakes Cohere at #9 🔹" [X Link](https://x.com/arena/status/1995534477813330298) 2025-12-01T16:44Z 112.9K followers, 3219 engagements "🚨New Models in the Arena 🐳DeepSeek V3.2: a new family of reasoning-first agent-oriented models from @deepseek_ai are now live in the Arena. Standard Thinking and Speciale are all in the Text Arena waiting for your toughest prompts Get your votes in: well see how they stack up soon" [X Link](https://x.com/arena/status/1995564824718442620) 2025-12-01T18:45Z 112.6K followers, 55.5K engagements "Explore the search leaderboard:" [X Link](https://x.com/arena/status/1996348689116471451) 2025-12-03T22:39Z 112.7K followers, 4314 engagements "🚨New Model Update @Amazon Nova X Lite is now available in the Text Arena Designed for medium-thinking reasoning tasks Nova X Lite is built for everyday tasks like helping customer support chats sorting documents and handling basic business workflows" [X Link](https://x.com/arena/status/1996396395411177920) 2025-12-04T01:49Z 112.5K followers, 12.2K 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 113.2K followers, 159.2K engagements "🚨🎬 New Video Model Update Kling O1 by @Kling_AI is ready for you in the Arena Kling O1 processes images and videos in a unified way enabling faster and more efficient content creation. Lets see how it does against the communitys most creative prompts. Your votes are essential for producing reliable data-driven rankings" [X Link](https://x.com/arena/status/1995644722048893285) 2025-12-02T00:02Z 113.2K followers, 13.6K engagements "🚨 Vision Leaderboard Update 🔸GPT-5.1-high ranks #3 (39pt increase since GPT-5-high) 🔸GPT-5.1 ranks #4 (24pt increase since GPT-5-chat) GPT-5.1 trails GPT-5.1-high by only two points making this an extremely tight race. Both models outrank every other GPT model on the Vision leaderboard sitting just behind Gemini-3-Pro and Gemini-2.5-Pro" [X Link](https://x.com/arena/status/1996735868158333008) 2025-12-05T00:18Z 113.2K followers, 14.5K engagements "Arena Expert launched last month as a new system for identifying the most difficult promptsthe kinds of questions people at the forefront of their fields are expected to ask. Since the launch we looked at how thinking and non-thinking models perform across both general and expert prompts. Heres what we found: Key takeaways: 🔷 The Expert Advantage helps differentiate model performance more effectively. 🔷 Thinking models score on average XX points higher than non-thinking models on Expert prompts. 🔷 Some notable exceptions occur such as Opus XXX (non-thinking) which scored XX points higher" [X Link](https://x.com/arena/status/1997018150068801911) 2025-12-05T19:00Z 113.2K followers, 12.6K engagements "Test DeepSeek V3.2 against the top frontier AI models in web development at:" [X Link](https://x.com/arena/status/1998242857061400763) 2025-12-09T04:06Z 113.2K followers, 5193 engagements "🚨Text Arena Update ERNIE-5.0-Preview-1103 by Baidu @ernieforDevs has landed on the Text leaderboard with a score of 1431 putting it in the top XX in the most competitive Arena. A few highlights: 🔹scores 1471 in the Software & IT Services Occupational field on par with GPT5.1-high 🔹scores 1464 in Coding on par with chat-gpt-4o The scores are still preliminary and well see how it converges. Congrats to the Ernie team" [X Link](https://x.com/arena/status/1998437959553716260) 2025-12-09T17:01Z 113.2K followers, 12.3K engagements "🚨Video Leaderboard Update Wan2.5-t2v-preview debuts at #7 on the Text-to-Video leaderboard continuing its strong performance after securing a Top X position on the Image-to-Video board last month. With a score of 1305 it now sits in a competitive Top XX group with Sora-2 and Veo-3. Congrats to the @Alibaba_Wan team for another solid performance 👏" [X Link](https://x.com/arena/status/1995997219049316559) 2025-12-02T23:23Z 113K followers, 13.7K engagements "Seedream XXX reaches #7 on the Text-to-Image leaderboard indicating an improved performance in the Arena. The update brings more cinematic rendering and improved lighting fidelity" [X Link](https://x.com/arena/status/1996641970673029608) 2025-12-04T18:05Z 113.2K followers, 3433 engagements "🚨🎬 Big news from Video Arena @GoogleDeepMinds latest Veo XXX now ranks #1 in both Text-to-Video and Image-to-Video leaderboards. 🏆 This is a +30-point leap from Veo XXX XXX making it the first model to break 1400 in Video Arena history Huge congrats to the @GoogleDeepMind team for pushing the frontier of video generation forward More details in the thread 🧵" [X Link](https://x.com/arena/status/1980319296120320243) 2025-10-20T17:04Z 113.2K followers, 460.1K engagements "🚨Text Leaderboard Update @xAIs Grok XXX (thinking) and Grok XXX have scaled new heights in the most competitive Text Arena: 🔹Grok XXX (thinking) lands at #1 with a score of 1483 🔹Grok XXX follows at #2 with a score of 1465 On the Arena Expert leaderboard: 🔸Grok XXX (thinking) also ranks at #1 with a score of 1510 🔸Grok XXX ranks at #19 with score of 1437 This is a 40+ point improvement since Grok X fast which landed in the Arena just two months prior. Congrats to the @xAI team for this incredible milestone 👏" [X Link](https://x.com/arena/status/1990530978943787291) 2025-11-17T21:22Z 113.2K followers, 5.2M engagements "🚨BREAKING: Text Leaderboard Update 🐳 Deepseek-v3.2 enters the leaderboard at #38 and Deepseek-v3.2-thinking lands at #41. For comparison previous versions ranked higher: 🔹 v3.2 ranks #38 (5 pts v3.1 and XX pts v3.2-exp) 🔹 v3.2-thinking ranks #41 (7 pts vs v3.1-thinking and X pts v3.2-exp-thinking) Both models show their biggest gains in Legal by rank with improvements of +28 points for v3.2 and +19 points for v3.2-thinking when compared to v3.1 predecessors. The largest drop appears in Healthcare for where v3.2-thinking falls by XX points. Where v3.2 performs strongest (among open" [X Link](https://x.com/arena/status/1996707563208167881) 2025-12-04T22:25Z 113.2K followers, 139.3K engagements "🚨 New Model in the Code Arena 🐳 DeepSeek V3.2 and V3.2-thinking are now ready for your toughest prompts in the next generation of live coding evaluations for frontier AI models. Weve seen how DeepSeek V3.2 performed in the Text Arena now lets see how it handles building real web apps. Remember your votes drive the leaderboards" [X Link](https://x.com/arena/status/1998242853898817820) 2025-12-09T04:06Z 113.2K followers, 61.7K 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 113.2K followers, 275.2K engagements "We put the top three Code Arena models head-to-head: Opus XXX Thinking 32k Opus XXX and Gemini X Pro. Theyre just XX points apart. Same tough prompts different results. Heres what stood out. Remember your votes drive the rankings. Watch how these contenders move on the leaderboard as more votes come in. Check out the comparisons in the thread below. 🧵" [X Link](https://x.com/arena/status/1993858153302380821) 2025-11-27T01:43Z 113.2K followers, 164K engagements "🚨BREAKING: @GoogleDeepMinds Gemini X Pro users are still going bananas. 🍌 The community has been voting on Nano Banana Pro with 2k resolution and it has claimed the top spot in major Arena categories vs. the default 1k variant. 🥇#1 in Text-to-Image (+8 point leap over nano-banana-pro) 🥇#1 in Image Edit (+10 point leap over nano-banana-pro) Benchmarking the 2k preview separately from the default 1k Nano Banana Pro reveals the true depth of the model's capabilities. Stay tuned for the 4k resolution coming soon. Congratulations to everyone at @GoogleDeepMind on this milestone" [X Link](https://x.com/arena/status/1995989152203243884) 2025-12-02T22:51Z 113.2K followers, 164.5K engagements "Test out Seedream XXX vs. all the top image generation models at:" [X Link](https://x.com/arena/status/1996641972875153857) 2025-12-04T18:05Z 113.2K followers, 2742 engagements "Deepseek-v3.2-thinking strongest open-model categories: 🔬 Life Physical & Social Science ⚖ Legal & Government Check out the details of the Expert and Occupational leaderboards here:" [X Link](https://x.com/arena/status/1996707568367128948) 2025-12-04T22:25Z 113.2K followers, 5492 engagements "Test out Deepseek V3.2 vs. all the best frontier AI at:" [X Link](https://x.com/arena/status/1996707570065854646) 2025-12-04T22:25Z 113.2K followers, 5078 engagements "📈Arena Trends Update We pulled Arena scores for the Top XX labs since the beginning of 2025 and the top climbers may surprise you. With tighter confidence intervals and new entries in the mix the Arena continues to shift. Stay tuned for more EOY insights and updates from the frontier" [X Link](https://x.com/arena/status/1998536014000959497) 2025-12-09T23:31Z 113.2K followers, 46.9K engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@arena lmarena.ai
lmarena.ai posts on X about ai, 6969, lmarenaai, agentic the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours.
Engagements: XXXXXX #
- X Week XXXXXXX -XX%
- X Month XXXXXXXXX +736%
- X Months XXXXXXXXXX -XX%
- X Year XXXXXXXXXX +70%
Mentions: XX #
- X Week XX -XX%
- X Month XXX +140%
- X Months XXX +84%
- X Year XXX +234%
Followers: XXXXXXX #
- X Week XXXXXXX +2.10%
- X Month XXXXXXX +16%
- X Months XXXXXXX +39%
- X Year XXXXXXX +90%
CreatorRank: XXXXXXX #
Social Influence
Social category influence technology brands XXXX%
Social topic influence ai #4682, 6969 #545, lmarenaai #1, agentic #260, categories #123, banana #1410, nano banana #362, open ai #1989, the world 2.9%, major #190
Top accounts mentioned or mentioned by @googledeepmind @grichm77 @zaiorg @alibabaqwen @xai @openai @googledeepminds @anthropicai @deepseekai @kimimoonshot @mistralai @grok @klingai @erniefordevs @elonmusk @henkpoley @dhtikna @achille610 @50hidalgo47 @saifmalik252
Top Social Posts
Top posts by engagements in the last XX hours
"🚨 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 XX - 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 🧵"
X Link 2025-09-19T23:41Z 113.2K followers, 4.6M engagements
"🖼🚨Image Leaderboard Update: The community has been busy comparing and voting on models over the weekend @bfl_mls FLUX.2 Pro and FLUX.2 Flex have landed on the Image leaderboards. Congrats to the @bfl_ml team 👏 Text-to-Image: 🔹FLUX.2 Flex ranks #2 🔹FLUX.2 Pro ranks #5 Image Edit: 🔹FLUX.2 Pro ranks #6 🔹FLUX.2 Flex ranks #7"
X Link 2025-12-01T22:27Z 113.2K followers, 24.7K engagements
"Gemini-3-pro-image-preview-2k (Nano Banana Pro) has claimed the #1 spot on the Text-to-Image Arena surpassing previous scores set by the Nano Banana variants. View the full leaderboard update here:"
X Link 2025-12-02T22:51Z 113.2K followers, 2073 engagements
"🌐 Search Leaderboard Update Two new contenders have arrived on the Search leaderboard: Gemini X Pro Grounding (@GoogleDeepMind) and GPT-5.1 (@openai). Current standings: 🥇 #1 gemini-3-pro-grounding 🥈 #2 gpt-5.1-search With a thin 9-point gap between both models the standings may shift quickly as more votes come in. Be sure to vote and stay tuned to see if these rankings hold This is shaping up to be one of the closest races on the leaderboard"
X Link 2025-12-03T22:39Z 113.2K followers, 21.8K engagements
"👇We want to know what you think. Put it to the test with your toughest prompts and lets see how it ranks:"
X Link 2025-12-04T01:49Z 113.2K followers, 4029 engagements
"🚨BREAKING: @GoogleDeepMinds Gemini-3-Pro is now #1 across all major Arena leaderboards 🥇#1 in Text Vision and WebDev - surpassing Grok-4.1 Claude-4.5 and GPT-5 🥇#1 in Coding Math Creative Writing Long Queries and nearly all occupational leaderboards. Massive gains over Gemini-2.5: 🔸WebDev in Code Arena: 1487 (+280 pts vs 2.5) 🔸Text: 1501 (+50 pts) 🔸Vision: 1328 (+70 pts) 🔸Arena Expert: Top-3 (just X pts behind #1) Huge congrats to the @GoogleDeepMind team on this breakthrough 👏"
X Link 2025-11-18T16:06Z 113.2K followers, 475.9K engagements
"🚨🎬 New Video Model update Kling Video XXX is ready in the Video Arena Created by @Kling_ai this is their first model with native audio. Kling Video XXX generates speech sound effects and ambient audio directly in sync with the visuals producing a complete video+audio output in a single step. Hang out with the Arena community and test it with your toughest prompts"
X Link 2025-12-05T00:53Z 113.2K followers, 10.5K engagements
"🚨BREAKING: New Leaderboard Updates Claude-Opus-4.5 and Opus-4.5 (thinking-32k) just landed on Code Arena (WebDev) and Text Arena leaderboards and Opus-4.5 instantly took #1 in WebDev leaderboard surpassing Gemini X Pro WebDev leaderboard (powered by Code Arena) 🥇#1 for Claude-Opus-4.5 (thinking-32k) 🥈#2 for Claude-Opus-4.5 Expert Leaderboard 🥇#1 for Claude-Opus-4.5 Text Leaderboard - #3 for Claude-Opus-4.5 - #6 for Claude-Opus-4.5 (thinking-32k) Huge congrats to the @AnthropicAI team for such incredible milestone Learn more in the thread on how it performs in key categories and on the"
X Link 2025-11-26T18:36Z 113.2K followers, 287.2K engagements
"🚨🖼 Image Leaderboard Update Seedream XXX by Bytedance has officially entered the Arena on both the Image Edit and Text-to-Image leaderboards. Here is where it landed: 🔹 #3 on Image Edit (score: 1338) 🔹 #7 on Text-to-Image (score: 1146) This update delivers a 27-pt increase over Seedream-4-2k and a 62-point gain over Seedream-3. This release raises the stakes on the Image Edit leaderboard outperforming Gemini XXX Flash Image (Nano Banana) and landing behind new top variants Nano Banana Pro and its 2k resolution which rank #2 and #1 respectively. Congrats to Bytedance on a strong showing 👏"
X Link 2025-12-04T18:05Z 113K followers, 13K engagements
"🚨 New Model in the Code Arena GPT-5.1-Codex Max by @OpenAI is ready for you in the Code Arena. Bring your most toughest creative prompts and we'll see how it stacks up against current leaders: Claude Opus XXX Thinking by @anthropicAI and Gemini X Pro by @GoogleDeepMind"
X Link 2025-12-04T21:27Z 113.2K followers, 24.3K engagements
"Remember your votes drive the leaderboards. Test GPT-5.1 Codex Max in the new Code Arena. 🧑💻 Code Arena is 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:"
X Link 2025-12-04T21:27Z 113.2K followers, 3711 engagements
"🚨Top XX Open Models by Provider for November The open model race continues with new models entering the Text Arena. Confidence intervals are getting tighter and the competition is heating up Here are the November Top 3: 🥇 #1 Kimi-K2-Thinking-Turbo by @Kimi_Moonshot (Modified MIT) 🥈 #2 GLM-4.6 from @Zai_org (MIT) 🥉 #3 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen (Apache 2.0) Recent releases of new proprietary models have reshuffled the universal rankings lowering the positions of some long-standing open models. Even so every open model still holds a strong place within the Top XXX on the"
X Link 2025-12-01T16:44Z 112.9K followers, 25.3K engagements
"Top XX Open Models by Provider shifts for November: ✨ New Entrants 🔹 Kimi-K2-Thinking-Turbo by @Kimi_Moonshot zooms to the top at #1 🚀 💪 Holding Firm 🔹 Qwen3-235b-a22b-instruct-2507 by @Alibaba_Qwen maintains at #3 🔹 Longcat-flash-chat by @Meituan_LongCat holds steady mid-pack at #5 🔹 MiniMax M1 by @minimax_ai stays at #6 🔹 Gemma-3-27b-it by @googledeepmind maintains at #7 🔹 Mistral-Small-2506 by @MistralAI hanging in at #8 🚶 Movers 🔹 Deepseek-V3.2-Exp-Thinking by @Deepseek_AI drops to #4 🔹 GLM-4.6 by @Zai_org drops to #2 🔹 GPT-oss-120b by @openAI overtakes Cohere at #9 🔹"
X Link 2025-12-01T16:44Z 112.9K followers, 3219 engagements
"🚨New Models in the Arena 🐳DeepSeek V3.2: a new family of reasoning-first agent-oriented models from @deepseek_ai are now live in the Arena. Standard Thinking and Speciale are all in the Text Arena waiting for your toughest prompts Get your votes in: well see how they stack up soon"
X Link 2025-12-01T18:45Z 112.6K followers, 55.5K engagements
"Explore the search leaderboard:"
X Link 2025-12-03T22:39Z 112.7K followers, 4314 engagements
"🚨New Model Update @Amazon Nova X Lite is now available in the Text Arena Designed for medium-thinking reasoning tasks Nova X Lite is built for everyday tasks like helping customer support chats sorting documents and handling basic business workflows"
X Link 2025-12-04T01:49Z 112.5K followers, 12.2K 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 2025-11-05T19:26Z 113.2K followers, 159.2K engagements
"🚨🎬 New Video Model Update Kling O1 by @Kling_AI is ready for you in the Arena Kling O1 processes images and videos in a unified way enabling faster and more efficient content creation. Lets see how it does against the communitys most creative prompts. Your votes are essential for producing reliable data-driven rankings"
X Link 2025-12-02T00:02Z 113.2K followers, 13.6K engagements
"🚨 Vision Leaderboard Update 🔸GPT-5.1-high ranks #3 (39pt increase since GPT-5-high) 🔸GPT-5.1 ranks #4 (24pt increase since GPT-5-chat) GPT-5.1 trails GPT-5.1-high by only two points making this an extremely tight race. Both models outrank every other GPT model on the Vision leaderboard sitting just behind Gemini-3-Pro and Gemini-2.5-Pro"
X Link 2025-12-05T00:18Z 113.2K followers, 14.5K engagements
"Arena Expert launched last month as a new system for identifying the most difficult promptsthe kinds of questions people at the forefront of their fields are expected to ask. Since the launch we looked at how thinking and non-thinking models perform across both general and expert prompts. Heres what we found: Key takeaways: 🔷 The Expert Advantage helps differentiate model performance more effectively. 🔷 Thinking models score on average XX points higher than non-thinking models on Expert prompts. 🔷 Some notable exceptions occur such as Opus XXX (non-thinking) which scored XX points higher"
X Link 2025-12-05T19:00Z 113.2K followers, 12.6K engagements
"Test DeepSeek V3.2 against the top frontier AI models in web development at:"
X Link 2025-12-09T04:06Z 113.2K followers, 5193 engagements
"🚨Text Arena Update ERNIE-5.0-Preview-1103 by Baidu @ernieforDevs has landed on the Text leaderboard with a score of 1431 putting it in the top XX in the most competitive Arena. A few highlights: 🔹scores 1471 in the Software & IT Services Occupational field on par with GPT5.1-high 🔹scores 1464 in Coding on par with chat-gpt-4o The scores are still preliminary and well see how it converges. Congrats to the Ernie team"
X Link 2025-12-09T17:01Z 113.2K followers, 12.3K engagements
"🚨Video Leaderboard Update Wan2.5-t2v-preview debuts at #7 on the Text-to-Video leaderboard continuing its strong performance after securing a Top X position on the Image-to-Video board last month. With a score of 1305 it now sits in a competitive Top XX group with Sora-2 and Veo-3. Congrats to the @Alibaba_Wan team for another solid performance 👏"
X Link 2025-12-02T23:23Z 113K followers, 13.7K engagements
"Seedream XXX reaches #7 on the Text-to-Image leaderboard indicating an improved performance in the Arena. The update brings more cinematic rendering and improved lighting fidelity"
X Link 2025-12-04T18:05Z 113.2K followers, 3433 engagements
"🚨🎬 Big news from Video Arena @GoogleDeepMinds latest Veo XXX now ranks #1 in both Text-to-Video and Image-to-Video leaderboards. 🏆 This is a +30-point leap from Veo XXX XXX making it the first model to break 1400 in Video Arena history Huge congrats to the @GoogleDeepMind team for pushing the frontier of video generation forward More details in the thread 🧵"
X Link 2025-10-20T17:04Z 113.2K followers, 460.1K engagements
"🚨Text Leaderboard Update @xAIs Grok XXX (thinking) and Grok XXX have scaled new heights in the most competitive Text Arena: 🔹Grok XXX (thinking) lands at #1 with a score of 1483 🔹Grok XXX follows at #2 with a score of 1465 On the Arena Expert leaderboard: 🔸Grok XXX (thinking) also ranks at #1 with a score of 1510 🔸Grok XXX ranks at #19 with score of 1437 This is a 40+ point improvement since Grok X fast which landed in the Arena just two months prior. Congrats to the @xAI team for this incredible milestone 👏"
X Link 2025-11-17T21:22Z 113.2K followers, 5.2M engagements
"🚨BREAKING: Text Leaderboard Update 🐳 Deepseek-v3.2 enters the leaderboard at #38 and Deepseek-v3.2-thinking lands at #41. For comparison previous versions ranked higher: 🔹 v3.2 ranks #38 (5 pts v3.1 and XX pts v3.2-exp) 🔹 v3.2-thinking ranks #41 (7 pts vs v3.1-thinking and X pts v3.2-exp-thinking) Both models show their biggest gains in Legal by rank with improvements of +28 points for v3.2 and +19 points for v3.2-thinking when compared to v3.1 predecessors. The largest drop appears in Healthcare for where v3.2-thinking falls by XX points. Where v3.2 performs strongest (among open"
X Link 2025-12-04T22:25Z 113.2K followers, 139.3K engagements
"🚨 New Model in the Code Arena 🐳 DeepSeek V3.2 and V3.2-thinking are now ready for your toughest prompts in the next generation of live coding evaluations for frontier AI models. Weve seen how DeepSeek V3.2 performed in the Text Arena now lets see how it handles building real web apps. Remember your votes drive the leaderboards"
X Link 2025-12-09T04:06Z 113.2K followers, 61.7K 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 2025-11-12T17:48Z 113.2K followers, 275.2K engagements
"We put the top three Code Arena models head-to-head: Opus XXX Thinking 32k Opus XXX and Gemini X Pro. Theyre just XX points apart. Same tough prompts different results. Heres what stood out. Remember your votes drive the rankings. Watch how these contenders move on the leaderboard as more votes come in. Check out the comparisons in the thread below. 🧵"
X Link 2025-11-27T01:43Z 113.2K followers, 164K engagements
"🚨BREAKING: @GoogleDeepMinds Gemini X Pro users are still going bananas. 🍌 The community has been voting on Nano Banana Pro with 2k resolution and it has claimed the top spot in major Arena categories vs. the default 1k variant. 🥇#1 in Text-to-Image (+8 point leap over nano-banana-pro) 🥇#1 in Image Edit (+10 point leap over nano-banana-pro) Benchmarking the 2k preview separately from the default 1k Nano Banana Pro reveals the true depth of the model's capabilities. Stay tuned for the 4k resolution coming soon. Congratulations to everyone at @GoogleDeepMind on this milestone"
X Link 2025-12-02T22:51Z 113.2K followers, 164.5K engagements
"Test out Seedream XXX vs. all the top image generation models at:"
X Link 2025-12-04T18:05Z 113.2K followers, 2742 engagements
"Deepseek-v3.2-thinking strongest open-model categories: 🔬 Life Physical & Social Science ⚖ Legal & Government Check out the details of the Expert and Occupational leaderboards here:"
X Link 2025-12-04T22:25Z 113.2K followers, 5492 engagements
"Test out Deepseek V3.2 vs. all the best frontier AI at:"
X Link 2025-12-04T22:25Z 113.2K followers, 5078 engagements
"📈Arena Trends Update We pulled Arena scores for the Top XX labs since the beginning of 2025 and the top climbers may surprise you. With tighter confidence intervals and new entries in the mix the Arena continues to shift. Stay tuned for more EOY insights and updates from the frontier"
X Link 2025-12-09T23:31Z 113.2K followers, 46.9K engagements