We tested Pangram, GPTZero, and Originality.ai on human and AI text. All three caught nearly every passage written from a simple prompt, but missed roughly one in five passages imitating a specific author's style.

The share of working days on which OpenAI's Codex collaborators merged very-high-effort code rose from about 2% in Q2 2025 to about 8% in Q2 2026.

GPT-4 topped Epoch's Capabilities Index (ECI) for roughly a year after its March 2023 release — no model since has led for as long. The second-longest reign, by o1, lasted barely three months.

Household income of weekly AI users ranges from 80% earning $100K+ for Claude to 37% for Meta AI in the Epoch AI/Ipsos survey.

Claude was the only AI tool to show significant usage growth across three Epoch AI/Ipsos survey waves in March-April 2026.

The best score on the Epoch Capabilities Index grew almost twice as fast over the last two years as it did over the two years before that, with a 90% acceleration in April 2024.

Epoch’s Capabilities Index stitches together benchmarks across a wide range of difficulties. We show how scores can be interpreted by mapping them back to expected benchmark performance.

Compared to Epoch internal evals, top labs report statistically consistent GPQA Diamond scores for their recent models.