Benchmarks / ML engineering

ML engineering

Train and tune models for a goal, for example Kaggle-style competitions.

Part of ML and research engineering.

• MLE-benchby OpenAIProject level · Any medal (%)

  64.4%Famou-Agent 2.0 (Gemini-3-Pro-Preview) · 23 Feb 2026

  Strong
• Terminal-Bench 4.0by Laude Institute and Stanford UniversityTask level · Resolution rate

  64.8%Claude Code + Opus 5.5 (max) · 6 Oct 2026

  Strong