[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.]

[@lmarena_ai](/creator/twitter/lmarena_ai)
"Were delivering a bundle of polish to the LMArena experience most of them inspired directly by your feedback 💬 Heres a look at whats new👇"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1945529822123626526) 2025-07-16 17:03:50 UTC 84.2K followers, 7122 engagements


"🚨 BREAKING: @Kimi_Moonshots Kimi-K2 is now the #1 open model in the Arena With over 3K community votes it ranks #5 overall overtaking DeepSeek as the top open model. Huge congrats to the Moonshot team on this impressive milestone The leaderboard now features X different providers in the top XX - the most competitive its ever been. More insights in the thread 🧵"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1945866381880373490) 2025-07-17 15:21:12 UTC 84.2K followers, 261.6K engagements


"Qwen 235b a22b (no thinking) is Alibaba's top open model ranking at #3 235B-a22b-no-thinking is a raw model without instruction tuning (thus "no thinking"). It's great at generation and ranks highly with the community due to it's raw reasoning power. Some other top open models with our community from Alibaba include: The 32B and 30B-a3b variants are smaller faster alternatives with solid performance though they trail behind the top-tier models. With 32B being denser among the two the community prefers it's accuracy over 30B-a3b. 30B-a3b is a MoE model making it a bit faster. qwq-32b is"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211515033612672) 2025-07-18 14:12:38 UTC 84.2K followers, 1959 engagements


"Packaging Design Prompt: A high-quality product photography image showcasing the "Honeybee Botanicals" an eco-friendly personal care line. Minimalist packaging in pastel colors. Label the Cleanser with text on two lines: "Honeybee Botanicals Cleanser" on the first line and "With Organic Shea Butter" on the second line. Label the Moisturizer with text on two lines: "Honeybee Botanicals Cream" on the first line and "For Ultra Hydration" on the second line. Label the smallest with text on two lines: "Honeybee Botanicals Liquid Gold" on the first line and "Improves Your Natural Glow" on the"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1947341733433643388) 2025-07-21 17:03:43 UTC 84.2K followers, 1942 engagements


"Kimi K2 - #1 in the Open Arena If you've been paying attention to open source models this new model from rising AI company Moonshot AI is making waves as one of the most impressive open-source LLMs to date. Our community tells us they also love they way Kimi K2 responds: Kimi is humorous without sounding too robotic. Kimi K2 is built on a Mixture-of-Experts (MoE) architecture with a total of X trillion parameters of which XX billion are active during any given inference. This design helps the model balance efficiency and on-demand performance"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211511674044641) 2025-07-18 14:12:37 UTC 84.2K followers, 2417 engagements


"MiniMax M1 makes the list with their top model ranking at #4 M1 also stands out for it's unique approach with MoE architecture combined with form of attention called "Lightning Attention" a linearized mechanism purpose-built for high-efficiency token processing. The approach definitely caught the attention of our community for being really good at dialogue reasoning and instruction-following"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211516673646711) 2025-07-18 14:12:39 UTC 84.2K followers, 1932 engagements


"Google DeepMind lands at #5 with their top open model Gemma X 27b it Gemma X is an open-weight multimodal language model. Gemma X can handle both text and image inputs excelling in reasoning long-context tasks and vision-language applications. Our community loves how this Gemma improved memory efficiency and increased support for larger context over the previous versions"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211518225522770) 2025-07-18 14:12:39 UTC 84.2K followers, 3002 engagements


"🚨 New contender enters the Arena: @xAIs Grok-4 is live Grok-4 debuts impressively at #1 across many hard benchmarks. Now its time to put it to the real-world test: challenge Grok-4 with your toughest prompts"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1943308658613588022) 2025-07-10 13:57:43 UTC 84.2K followers, 826.8K engagements


"Check out the latest Computer Agent Arena leaderboard"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1936564392356975102) 2025-06-21 23:18:25 UTC 84.2K followers, 15.3K 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 🙌"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1896675400916566357) 2025-03-03 21:33:48 UTC 84.2K followers, 5.9M engagements


"🖼 Bytedance's Seedream XXX is in the Arena Tied at #4 with top Text-to-Image models: - Flux X Kontext Max & Pro @bfl_ml - Imagen XXX Generate @googledeepmind Let's see how it does with a few use cases 👇🧵"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1947341726534013391) 2025-07-21 17:03:42 UTC 84.2K followers, 4755 engagements


"Photorealism Prompt: A photorealistic portrait of a young man with striking blue eyes. He wears a gentle serene expression. Shot outdoors during golden hour with warm sunlight backlighting his auburn hair and a soft bokeh background of greenery"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1947341731013530047) 2025-07-21 17:03:43 UTC 84.2K followers, 1962 engagements


"Grok-4 was tested with real-world prompts across domains like coding math as well as creative writing. It ranks Top-3 across the board: ➗ Math: #1 💻 Coding: #2 ✍ Creative Writing: #2 📋 Instruction Following: #2 🧠 Hard Prompts: #3"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1945146351785795641) 2025-07-15 15:40:03 UTC 84.1K followers, 11.9K engagements


"DeepSeek's top open model DeepSeek R1-0528 ranks #2 R1-0528 is a refined instruction-tuned version of R1 and the #2 best open chat model according to the community. Strong in multi-turn dialogue and reasoning tasks. R1 (baseline) is the original still solid but now slightly behind newer tuning variants. V3-0324 is a MoE model with 236B total parameters but activates only a few experts per prompt. This makes it both powerful and efficient. It performs well across instruction reasoning and multilingual tasks but prompt format matters more here than with R1-0528"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211513322344512) 2025-07-18 14:12:38 UTC 84.2K followers, 2037 engagements


"🧵Top XX Open Models by Provider Though proprietary models often top the charts open models are also paired in battle mode and ranked on our public leaderboards. Here are the top XX when stacked by top open model by provider. - #1 Kimi K2 (Modified MIT) @Kimi_Moonshot - #2 DeepSeek R1 0528 (MIT) @deepseek_ai - #3 Qwen 235b a22b no thinking (Apache 2.0) @alibaba_qwen - #4 MiniMax M1 (MIT) @minimax_ai - #5 Gemma X 27b it (Gemma) @googledeepmind - #6 Mistral Small Ultra (Apache 2.0) @mistral_ai - #7 Llama XXX Nemotron Ultra 253b v1 (Nvidia Open Model) @nvidia - #8 Command A (Cohere) @cohere - #9"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1946211508335333676) 2025-07-18 14:12:37 UTC 84.2K followers, 42.8K engagements


"In case you missed it: Grok X by @xai is in the Arena 🚀 Start asking your hardest prompts Side by Side vs. all the best frontier AI We'll see if it performs as well with real-world scenarios as it did with hard benchmarks"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1943717908128972852) 2025-07-11 17:03:56 UTC 84.2K followers, 39.8K engagements


"🚨 BIG NEWS 🚨 Search Arena is live with X top models with search capabilities ready for testing. Be sure to have the "Search" modality selected in the chat box and get testing. 🌐 @xAi: Grok X @anthropic: Claude Opus X @perplexity: Sonar Pro High & Reasoning Pro High @openAI: o3 & GPT 4o-Search Preview @googledeepmind: Gemini XXX Pro Grounding"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1948053410139541626) 2025-07-23 16:11:40 UTC 84.2K followers, 25.1K 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 🧵"  
![@lmarena_ai Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::1641378826537295874.png) [@lmarena_ai](/creator/x/lmarena_ai) on [X](/post/tweet/1945146348203905063) 2025-07-15 15:40:03 UTC 84.2K followers, 482K engagements