Log inSign up
user avatar
Arena.ai
@arena
Where AI meets the real world. Formerly LMArena. We measure and advance the frontier of AI through community-driven evaluation. We’re hiring → arena.ai/jobs
US
arena.ai
Joined March 2023
217
Following
182.4K
Followers
AffiliatesRepliesMedia
  • Pinned
    user avatar
    Arena.ai
    @arena
    Jun 4
    Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image
    00:42
  • user avatar
    Arena.ai
    @arena
    1h
    Kimi-K3 just topped the Frontend Code Arena with a 76% pairwise win rate. When its output was compared head-to-head against other models on the same task, it was picked as the better output 76% of the time on average. For reference: Claude Fable 5 (63%), GPT-5.6 Sol (58%). 50%
    user avatar
    Arena.ai
    @arena
    6h
    Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics,
  • user avatar
    Arena.ai
    @arena
    4h
    In the Text Arena, Kimi-K3 by @Kimi_Moonshot landed #9, with 1486 pts. This is another significant improvement from Kimi-k2.6 (#38 -> #9). - Top 10 in Creative Writing, Coding and Instruction Following - #1 in three occupations: Physical & Social Science, Legal & Government,
    user avatar
    Kimi.ai
    @Kimi_Moonshot
    5h
    Introducing Kimi K3: Open Frontier Intelligence 🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal 🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts 🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional
  • user avatar
    Arena.ai
    @arena
    5h
    Kimi K3 from @Kimi_Moonshot has moved the Pareto Frontier for Code Arena: Frontend.
    user avatar
    Arena.ai
    @arena
    6h
    Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics,
  • Arena.ai reposted
    user avatar
    Kimi.ai
    @Kimi_Moonshot
    5h
    🤯
    user avatar
    Arena.ai
    @arena
    6h
    Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics,
  • user avatar
    Arena.ai
    @arena
    5h
    Replying to @arena
    Check out @Kimi_Moonshot's Kimi-K3 official release:
    user avatar
    Kimi.ai
    @Kimi_Moonshot
    5h
    Introducing Kimi K3: Open Frontier Intelligence 🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal 🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts 🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional
  • user avatar
    Arena.ai
    @arena
    6h
    Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics,
    00:56
    user avatar
    Kimi.ai
    @Kimi_Moonshot
    6h
    Meet Kimi K3
  • user avatar
    Arena.ai
    @arena
    7h
    Replying to @arena
    In the Text Arena, Inkling also landed at #10 for open source (1447 pts), and #58 overall. It is the #2 open source model from the US, second to GoogleDeepMind’s Gemma-4-31B. Highlights across key categories: - #10 Hard prompts - #12 Longer Query - #14 Coding - #15 Instruction
Arena.ai (@arena) / X