NerfBench weekly: Astra at 97.1%, Opus 5.5 rebounds to 105.8%

Bridgebench @bridgebenchOriginally posted 2026.10.16

Open original on X

This week's NerfBench results are live. No nerfs detected. Claude Opus 5.5: 105.8% Claude Sonnet 5.5: 98.9% GPT 6.1 Sol: 98.0% GPT 6 Astra: 97.1% The big story is Opus 5.5. It jumped 10 points in a week, from 95.7% to 105.8%. Last week it was the only model below its launch score. This week it's the only one above it. Opus 5.5 is getting stronger.