Skip to content

Formats · Latest news

Evals & benchmarks

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

221 top picks all-time · 99 in the past 30 days · chosen from 1,314 items collected all-time

Latest pick

Top picks archive · Page 12

Top picks 221–221 of 221

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.