Terminal-Bench-Science: Evaluating AI agents on scientific research workflows

2 hours ago (terminal-bench-science.ai)

I'm glad to see that GPT Sol beats Opus at least in Mathematical Sciences, because that's my need right now, and I much prefer GPT's prose style.

Damn. These things aren't AGI... but I don't care.

Luna is good enough for me to give a parser spec and have it write one.