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.
More from coding & agent
- New Benchmark: 200+ Sokoban Rooms to Test Agent Planning Skills — generativist · 2026-07-31
- Alibaba's Qwen-UI-Agent: SOTA on Mobile Use, Beats GPT-4o — AlibabaTongyiLab · 2026-07-31
- LedgerMind Tackles Multimodal Agent Hallucination via Structured Evidence Ledgers — Enjun Du · 2026-07-31
- AI Tour Meeting: A Multi-Agent Framework for Group Travel Planning — Daisuke Kikuta · 2026-07-31
- App Store Connect CLI 3.3.0 Released with Hardened Security and Submission Handling — rudrank · 2026-07-31
- Cloudflare Details Internal Agent Platform Security After OpenAI and Anthropic Sandbox Escapes — irvinebroque · 2026-07-31