Agent Harness Model Achieves Frontier Performance at <1% Compute Cost – Introducing Macaron‑V1‑Preview

A 30‑person lab trained a 749B‑parameter Agent model called Macaron‑V1‑Preview using fewer than 300 GPUs, achieving less than 1% of the compute cost of comparable models while matching state‑of‑the‑art performance on real‑world Agent benchmarks such as LivingBench, VitaBench, A2UI and PinchBench.

AIAgentEfficient Training

0 likes · 15 min read

Agent Harness Model Achieves Frontier Performance at <1% Compute Cost – Introducing Macaron‑V1‑Preview

Machine Learning Algorithms & Natural Language Processing

Jun 8, 2026 · Artificial Intelligence

MindLab Unveils 749B Agent-Optimized Macaron‑V1‑Preview Model

MindLab released the 749B‑parameter Macaron‑V1‑Preview, a model engineered for deep Agent‑Harness post‑training that was trained on fewer than 300 GPUs at less than 1% of the compute cost of peer models and achieves SOTA results on multiple Agent‑centric benchmarks such as LivingBench, VitaBench and PinchBench.

Agent HarnessEfficient TrainingLoRA

0 likes · 16 min read

MindLab Unveils 749B Agent-Optimized Macaron‑V1‑Preview Model