Mithil Vakde · Efficient ARC-AGI Model

mdlARC

A 75M-parameter transformer trained from scratch for about 67 cents reaches 44% on ARC-AGI-1 - no LLM involved, and among the best low-cost scores on that benchmark. Ships the full dataset-building pipeline and three training intensity modes, with a run taking roughly two hours on an RTX 5090 over PyTorch, numba and flash-attn. MIT. Set against everything else that shipped this week, the most quietly striking result of the seven days.