debugml.github.io

Finding Widespread Cheating on Popular Agent Benchmarks (opens in new tab)

Covered by 3 sources See all sources covering this story including GitHub, agents-last-exam.orgDiscussed on Hacker News

Agentic cheating is a widespread issue, affecting thousands of submitted agent runs on 28+ submissions across 9 different benchmarks.

Read the original article
Sign in to keep reading the full article.
Sign UpLog In

Covered in 3 articles

GitHub·

Proctor – signed isolation bundles for AI coding-agent benchmarks

Discussed on Hacker News
Feeds
agents-last-exam.org·

AI Agent Benchmark for Real-World Professional Workflows

Discussed on Hacker News and Hacker News
Feeds
tbench.ai·

Leaderboard Integrity Update at terminal-bench

Discussed on Hacker News
Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help