Skip to content

Formats · Latest news

Evals & benchmarks

Model results, disputes about evaluation methods, and leaderboard changes.

361 top picks all-time · 206 in the past 30 days · chosen from 2,743 items collected all-time

Latest pick

Top picks archive · Page 19

Top picks 361–361 of 361

Mar 11, 2024

Mar 11, 2024Mon
  1. Cognition Blog (Devin, Windsurf)OfficialAI score88

    Cognition introduces Devin, an AI agent that works on software engineering tasks

    AICognition introduces Devin as an AI software engineer that can plan and execute complex engineering tasks with a shell, code editor, and browser.

    Why it matters: The post pairs Devin's end-to-end task demos with SWE-bench results against prior models, letting readers weigh the claimed capability against the evaluation setup.