1. X
  2. LLM Stats
Log inSign up
LLM Stats
381 posts
Image
user avatar
LLM Stats
@LlmStats
Independent AI evaluations lab. Step 1: Accurately measure intelligence/watt/sec across all domains.
llm-stats.com
Joined February 2025
108
Following
1,756
Followers
AffiliatesAffiliatesRepliesRepliesArticlesArticlesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • LLM Stats reposted
    user avatar
    Mark Santos
    @markksantos
    6h
    🚨Kimi K3 BEATS Opus 4.8! K3 is in 3rd place on the ArtificialWatch Index🥉 Here's how the Index is computed: 💠 Best Variant Wins: Models are scored using only their top-performing version, ensuring a fair, identical comparison for everyone. 💠 Percentiles, Not Averages:
    Image
    3.8K03.8K
  • LLM Stats reposted
    user avatar
    Mark Santos
    @markksantos
    Jul 15
    Everyone wants to know what the best AI model is. So I combined all the top AI benchmarks in one place. - LiveBench - @arena - SimpleBench - @LlmStats - @bridgebench Creating what I call the ArtificialWatch Index. GPT-5.6 is taking the lead, though I still personally
    Image
    3250325
  • LLM Stats reposted
    user avatar
    Ryan Shea
    @ryaneshea
    Jun 26
    Replying to @lillian_ma_ @METR_Evals and 4 others
    Great list! Here are some more fantastic AI eval labs: @ValsAI (publishes one of the most comprehensive and high quality set of benchmarks) @EpochAIResearch (publishes FrontierMath, the highest quality set of math evals) @Designarena (publishes the highest quality set of
    user avatar
    Lillian Ma
    @lillian_ma_
    Jun 25
    some AI evals labs + builders worth following: @METR_Evals (@BethMayBarnes) Independent evals for the uncomfortable question: can frontier models actually do dangerous autonomous work, or are we mostly measuring test-taking? @arcprize (@fchollet, @mikeknoop) The benchmark
    1.1K01.1K
  • user avatar
    LLM Stats
    @LlmStats
    Jun 25
    @Unisound_AI has launched U2, and we've independently benchmarked it on LLM Stats. U2 is a 266B-parameter sparse model with just 10B active parameters (3.8% of total), priced at $0.15 / $0.30 per 1M input/output tokens ($0.003/M cached input). Unisound positions it around three
    Image
    6270627
    user avatar
    LLM Stats
    @LlmStats
    Jun 25
    Full independent results:
    llm-stats.com
    U2 Benchmarks, Pricing & Context Window
    Unisound has launched its next-generation flagship model, Unisound U2, built around three core advances: high intelligence density, high token efficiency, and a native agent architecture. Through...
    1770177
    user avatar
    LLM Stats
    @LlmStats
    Jun 25
    Detailed model breakdown:
    Image
    Unisound U2: Benchmarks, Pricing, and Full Specs
    From llm-stats.com
    1350135
  • user avatar
    LLM Stats
    @LlmStats
    Jun 17
    NEW: Zhipu AI released GLM-5.2 (753B parameters) on June 16, 2026, and it lands #3 on the LLM Stats Index. The standout feature: a 1M-token context window (5x jump from GLM-5.1's 200K) with 131K output tokens, plus two thinking-effort levels (High/Max recommended for complex
    Image
    7490749
    user avatar
    LLM Stats
    @LlmStats
    Jun 17
    Full model breakdown here:
    llm-stats.com
    GLM-5.2 Benchmarks, Pricing & Size
    GLM-5.2 is Z.AI's flagship foundation model built for long-horizon tasks, delivering a solid 1M-token context that stably sustains long, messy coding-agent trajectories. It improves substantially...
    2180218
  • user avatar
    LLM Stats
    @LlmStats
    May 28
    PROGRESSION: Claude Opus 4.8 (@AnthropicAI) sets a new high on LLM Stats Index after 3 years of progress. > 68 on LLM Stats Index > Frontier gained 85 index points over the 3.3-year window This shifts the predictions towards a more optimistic scenario of complete benchmarking
    Image
    1K01K
  • user avatar
    LLM Stats
    @LlmStats
    May 28
    NEW #1: Claude Opus 4.8 (@AnthropicAI) takes the top spot on LLM Stats Index. > 68 on LLM Stats Index > +5 over previous SOTA (GPT-5.5)
    Image
    5050505
  • user avatar
    LLM Stats
    @LlmStats
    May 19
    NEW: Gemini 3.5 Flash (@GoogleDeepMind) lands at #5 on LLM Stats Index. >4x faster than other frontier models >$1.50 / $9 per 1M tokens It's significantly faster than other frontier models and the quality has increased significantly. It's also the best tool calling model
    Image
    8770877
    user avatar
    LLM Stats
    @LlmStats
    May 19
    Full model breakdown:
    llm-stats.com
    Gemini 3.5 Flash Benchmarks, Pricing & Context Window
    Gemini 3.5 Flash is Google's strongest agentic and coding model in the Flash series, delivering frontier-level performance at up to 4x the speed of comparable frontier models and often at less than...
    2910291
  • LLM Stats reposted
    user avatar
    Arvind’s Broody
    @rks_agent
    May 8
    @LlmStats' index predicts benchmark saturation by mid-2027. GPT-5.5 leads, but human-knowledge evals are topping out. Surprised me, now focusing on intelligence per watt and inference speed. That's the ceiling for agent productivity in real workflows.
    7470747
  • LLM Stats reposted
    user avatar
    チェリ@AIエンジニア•メタAIインフルエンサー
    @rN1oO71GTPiEMks
    May 6
    LLM Statsが、主要AIモデルを性能、速度、価格で比較する最新リーダーボードを紹介しました。公式ページではClaude Mythos Previewが推論、Gemini 3.1 Proがコーディング、Mercury 2が出力速度で目立つと整理されています。
    user avatar
    LLM Stats
    @LlmStats
    May 6
    Today we're introducing the LLM Stats Index. For 3.2 years, we've tracked every frontier model release. The Index aggregates 200+ benchmark results into a single TrueSkill rating per model, spanning law, healthcare, coding, tool calling, vision, and reasoning. Across every
    Image
    7320732
  • user avatar
    LLM Stats
    @LlmStats
    May 7
    NEW: GPT-5.5 Instant is now available on LLM Stats. Try it now for free in our agent and code playgrounds.
    Image
    3480348
  • user avatar
    LLM Stats
    @LlmStats
    May 7
    NEW: Grok 4.3 is out from @xai. Now available on LLM Stats.
    Image
    4380438
  • user avatar
    LLM Stats
    @LlmStats
    May 6
    Today we're introducing the LLM Stats Index. For 3.2 years, we've tracked every frontier model release. The Index aggregates 200+ benchmark results into a single TrueSkill rating per model, spanning law, healthcare, coding, tool calling, vision, and reasoning. Across every
    Image
    2.7K02.7K
  • user avatar
    LLM Stats
    @LlmStats
    Apr 24
    This is by the end of the week the AI Leaderboard after the releases of DeepSeek V4, Kimi 2.6, GPT-5.5 and Claude Mythos.
    Image
    8490849
    user avatar
    LLM Stats
    @LlmStats
    Apr 24
    This is the AI Coding Leaderboard by the end of the week:
    Image
    6510651
    user avatar
    LLM Stats
    @LlmStats
    Apr 24
    See the full leaderboards at: llm-stats.com @OpenAI @AnthropicAI @Kimi_Moonshot @deepseek_ai
    Image
    AI Leaderboard 2026: Compare & Rank 300+ Top AI Models by Intelligence, Speed & Price
    From llm-stats.com
    2080208
Advertisement
Advertisement