Skip to content

Formats · Latest news

Evals & benchmarks

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

261 top picks all-time · 137 in the past 30 days · chosen from 1,768 items collected all-time

Latest pick

Top picks archive · Page 14

Top picks 261–261 of 261

Mar 11, 2024

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

    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.