We are publishing 4 new benchmark reviews: 1 is Verified, and 3 are Flawed. 4 more benchmarks lacked sufficient information to assign a verd...

We recorded over a thousand runs of Slay the Spire and its sequel for our recent benchmark, SpireClimb. Over the coming weeks, we'll publish...

How far behind the closed frontier are open-weight cyber capabilities? About 6–7 months. Zai’s GLM-5.3 is the highest-scoring open-weight m...

The New York Times visualizes the staggering amount of math needed to train AI models, using data from Epoch's research teams 📊 https://ww...

Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166)...

Six months ago, frontier AI models could barely beat Slay the Spire. Now, according to our new SpireClimb benchmark, they win 90%+ of runs a...

In 3 of the 18 math subfields we track, more than half of arXiv papers by established authors now acknowledge using AI. Rates have increase...

A new architecture for GPT-6.1 Sol? OpenAI halved its cached-input price compared with GPT-6 Sol. Our measurements show it also handles lon...

Can AI automate Epoch? We're introducing Epoch Automation Reports to evaluate frontier models on realistic, open-ended tasks drawn from our ...

AI developers aim to create an automated AI researcher. How close are they? To find out, we built InnovationEval, which tests whether AI ca...

We introduced two new experimental settings to our long-horizon board game benchmark, EBR-bench: banning the game’s strongest card and a mul...

The share of US adults experiencing a cyber incident hasn't grown since Claude Fable 5's release. About 45% reported at least one incident ...

How do Chinese AI firms make money? In a new report, @cherylwoooo and @ansonwhho identify five revenue sources and analyze how much each con...

Who is more exposed to a semiconductor supply shock, China or the US? We split out semiconductors in the ICIO tables economists use to trac...

OpenAI recently published data on its researchers’ coding-agent usage. We took their weekly figures from January to mid-August 2026 and fitt...

We estimate AI infrastructure could soon support hundreds of millions or even billions of AI agents. At the high end, that’s enough to rival...

We’ve collected metadata on the usage patterns of 5,000 ChatGPT users and made it available in our new ChatGPT usage explorer. The historie...

Claude Opus 5.5 has taken the top spot on the Epoch Capabilities Index (ECI) with a score of 167, narrowly ahead of GPT-6 Astra. Claude Son...

Can AI tell if you've built your IKEA furniture wrong? Our new benchmark, the Furniture Assembly Benchmark (FAB), gives models the manual an...

AI is getting cheaper more quickly than any other transformative tech in history. At a given level of performance, cost has fallen ~47%/quar...