Frontis-MA1 (35B) Open-Sourced: Achieves 71.21% Medal Average on MLE-Bench, Approaching GPT-5.6

FrontisAI · hf · 2026-07-31

FrontisAI releases Frontis-MA1 (35B), a meta-evolution agent for ML engineering, and the OpenMLE stack. On MLE-Bench Lite with 12-hour budget on one RTX 4090, Frontis-MA1 improves Medal Average from 39.39% to 60.61% with OpenMLE-Evo, and 71.21% with OpenMLE-Evo-Max, surpassing GPT-5.5 + Codex and approaching GPT-5.6 Sol and Kimi K3. On NatureBench Lite, model and framework transfers raise Match-SOTA from 50% to 70% and 20% to 50% respectively.

Original post →

More from coding & agent

coding & agent channel →