I think Epoch does a great job benchmarking, but I continue to believe that open weights models are much more fragile, especially out-of-dis…

I think Epoch does a great job benchmarking, but I continue to believe that open weights models are much more fragile, especially out-of-distribution, than their benchmarks indicate. Vibe-wise, I don’t think they were only 3 months behind last year or only 4 months behind today. We measure the gap using the Epoch Capabilities Index, our aggregate measure of model capability. Compared to our last analysis, the gap has widened slightly — we previously estimated an average gap of three months between January 2023 and October 2025.

Source: Ethan Mollick (X) | 2026-05-30