Terminal test runs won't catch multi-turn agent regressions. In Ep 3 of Agent Clinic, Dani Zamora & @matt_feroz build an automated eval suite for a LangGraph agent in 60 mins. Here's the 4-step framework to go from vibes to benchmark ANY AI agent →

Terminal-Bench-Science discriminates well between models, as well as between different reasoning effort levels within frontier models. Claude Opus 5.5 rises ~38 points from low effort at 24% to xhigh at 62%, alongside a 5x difference in the cost per task. Max effort for Opus 5.5 scores slightly below xhigh at 59%. GPT-6 Sol gains 27 points from low to max effort at ~7.5x the cost per task.

Terminal games, reimagined over P2P. 🕹️ Meet RandomSpacer — an arcade space-shooter built entirely in the terminal for the Aleph Hackathon (Pear Track). Inspired by Asteroids and Space Invaders, it packs real-time multiplayer, rankings, and zero central servers. 🎥 Watch the demo: 🔗 Project details:

TerminalBench did a great job with 4.0, highly recommend anyone interested in benchmarking read more about it, they put together a pretty detailed blog post that I've read twice now! I have a ton of respect for what @ryan_marten is doing, learning a lot from him as I make my way in the wild world of benchmarking.

Terminal-Bench 4 waffle view of tasks & models across 5 attempts is fire 🔥 gives you a pretty good idea of which tasks are saturated and which ones sit at the edge of frontier capability