Micah Hill-Smith
@_micah_h
Followers
645
Following
3K
Media
7
Statuses
151
Co-founder & CEO @ArtificialAnlys. Previously @McKinsey.
Sydney
Joined August 2011
RT @ArtificialAnlys: xAI gave us early access to Grok 4 - and the results are in. Grok 4 is now the leading AI model. We have run our full….
0
2K
0
RT @ArtificialAnlys: We are hiring! We’re looking for engineers and researchers who want to build the standard for how the world evaluates….
0
4
0
Excited to share highlights from our latest Artificial Analysis State of AI report! . It's been a huge team effort leveraging data from everything we do - intelligence evals, performance, cost, preference votes and more.
Launching our latest quarterly Artificial Analysis State of AI Report: Our analysis of the key trends shaping AI. A highlights version of the report is available for download on our website for a limited time. We unpack 6 trends defining AI in early 2025:.1.⚡ The race for
0
0
11
RT @ArtificialAnlys: Llama 4 provider benchmarks: Faster and cheaper than Llama 3.3 70B. We are now benchmarking over 10 providers of Llama….
0
17
0
RT @ArtificialAnlys: Llama 4 Intelligence Index Update: We have now replicated Meta’s claimed values for MMLU Pro and GPQA Diamond, pushing….
0
166
0
RT @ArtificialAnlys: Llama 4 independent evals: Maverick (402B total, 17B active) beats Claude 3.7 Sonnet, trails DeepSeek V3 but more effi….
0
91
0
RT @ArtificialAnlys: Launching our 2025 State of AI Survey! Take part to receive the full survey report and win a pair of Meta Ray-Bans 🕶️….
0
5
0
RT @ArtificialAnlys: DeepSeek takes the lead: DeepSeek V3-0324 is now the highest scoring non-reasoning model. This is the first time an op….
0
648
0
RT @ArtificialAnlys: The Halfmoon 🌓 reveal: Congratulations to @reveimage on creating the world’s leading image generation model with Reve….
0
43
0
RT @ArtificialAnlys: Gemma 3 27B’s Intelligence vs. Size positioning is compelling compared to other smaller, open weights models. We have….
0
18
0
RT @volokuleshov: This is really cool---@ArtificialAnlys benchmarked the Mercury diffusion language models. Mercury reaches 1000 tok/sec wh….
0
3
0
RT @ArtificialAnlys: Thanks @chamath for the shoutout on the @theallinpod this week!. Here’s our latest Frontier Model Intelligence Over Ti….
0
1
0
RT @ArtificialAnlys: xAI arrives at the frontier: Grok 3 is poised to be the world’s new leading model, likely only surpassed by OpenAI’s u….
0
99
0
Very excited to announce this upgrade - a project we've been working on for a long time. Much more to release from this work over the coming days too!.
Announcing Artificial Analysis Intelligence Index V2 - the biggest upgrade to our eval suite yet. Summary of Intelligence Index V2:.➤ Harder evals: MMLU-Pro, HLE (Humanity's Last Exam), GPQA Diamond, MATH-500, AIME 2024, SciCode, and LiveCodeBench - see below for a description
1
0
6
RT @NVIDIAAIDev: 👀 The most capable hardware plus the broadest inference software ecosystem means the shortest path to optimal performance,….
0
17
0
RT @ArtificialAnlys: Comparing DeepSeek R1 APIs: We are now tracking DeepSeek R1 APIs from @DeepInfra, @FireworksAI_HQ , @togethercompute,….
0
25
0
RT @ArtificialAnlys: Google’s Gemini 2.0 Flash is out of preview, and gets a small intelligence boost - now an incredibly powerful model pr….
0
32
0
RT @ArtificialAnlys: Announcing Artificial Analysis State of AI: China 🇨🇳. For the first time, we are charting the rise of China’s top AI c….
0
107
0