ResearchAug 29, 2026 · 12:375 sources
Terminal Bench 4.0 Debuts 66 Tasks In Expanded AI Agent Evaluation
From huggingnews.com
Developers released Terminal-Bench 4.0, an updated dataset and leaderboard featuring 66 tasks across categories including science, software, and security. The update includes a new Terminal-Bench-Science track for research workflows. Early results indicate Opus 5 outperformed Fable 5, and GLM 5.3 is the top open source model.
Read the sourceSign in to suggest
Sources
+ 4 more
- SUPPORT@himanshustwts“GLM 5.3 is best open source model out there sharing very close boundary with Fable 5”x.com
- SUPPORT@zixuanli_“pushed a version update to the Terminal-Bench dataset and leaderboard”x.com
- SUPPORT@andykonwinski“benchmark for evaluating AI agents on research workflows across scientific do…”x.com
- SUPPORT@jun_song“Those benchmark scores are from before the nerfs, and right now both are heavily degraded”x.com
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today