Terminal-Bench-Science

Headlines · 1

1. 4d
   Artificial Analysis overhauls Intelligence Index with private evaluations

   Artificial Analysis launched Intelligence Index v5, with 60% of its evaluations now based on private test sets or held-out answers. The update adds FrontierCode 2.0 and Terminal-Bench-Science, upgrades three existing benchmarks, and introduces Progress Index v1 to track model capability over time; Claude Opus 5.5 leads the initial v5 ranking with 58 points.

   cognition (X) · 🔥 5

Experience and discussion from the community

Share my Terminal-Bench-Science experienceAsk about Terminal-Bench-Science