Back to article
tbench.ai

Terminal-Bench: a benchmark for AI agents in terminal environments (opens in new tab)

Covered by 15 sources See all sources covering this story including Blog on Tailscale, Kilo BlogDiscussed on Hacker News and Hacker News

Covered in 16 articles

Blog on Tailscale·

A simpler way to experiment with AI coding agents using Aperture CLI

Feeds
Kilo Blog·

KiloBench - Because Your Benchmark Score Doesn't Pay the Bill

Feeds
goose-docs.ai·

Self-Improving Agents Still Need Humans

Discussed on Hacker News
Feeds
The New Stack·

Cursor bets on cheaper coding with Composer 2.5 and Kimi K2.5

Feeds
venturebeat.com·

Google says Gemini 3.5 Flash can slash enterprise AI costs by more than $1 billion a year

Feeds
venturebeat.com·

AI IQ is here: a new site scores frontier AI models on the human IQ scale. The results are already dividing tech.

Feeds
Tom's Guide
·

Google just launched Gemini 3.5 Flash

Feeds
agents-last-exam.org·

AI Agent Benchmark for Real-World Professional Workflows

Discussed on Hacker News and Hacker News
Feeds
henrypan.com·

What 1,000+ Harness Experiments Taught Me About Self-Improving Agents

Discussed on Hacker News and Hacker News
Feeds
andrewjesson.com·

The engineering practices Claude Code and Codex use to improve AI agents

Discussed on Hacker News
Feeds

In other languages

Xataka·

Hay una batalla por tener el modelo de IA que programa mejor. Y en ella ha aparecido un rival bueno, bonito y muy barato: Cursor

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