Roundtable Research company blog

Benchmarking leading AI agents against Google reCAPTCHA v2

by Mathew Hardy, Mayank Agrawal, Milena Rmus research.roundtable.ai published 2025-10-306 min read

We evaluate three leading AI models—Claude Sonnet 4.5, Gemini 2.5 Pro, and GPT-5—on their ability to solve Google reCAPTCHA v2 challenges and find significant performance differences, with success rates ranging from 28% to 60%.

Points

124

HN comments

97

Submissions

1

Cited by

0 commenters

AI & Machine LearningSecurity & Privacy2025

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

RRikiya Takehi20262,960 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,889 points642 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details