Morgan(@morganlinton):Update on my Opus 5.5 benchmark with @VulcanBench As many of you know, I don't get early access to these models, so I can only start benchmarking the day the model is released. It looks like something in my eval suite is being refused by Claude Code's safety classifier, and is then falling back on Opus 4.8. Looking into this more, reviewing the traces now. But likely going to be a bit longer for me to get the benchmarks out, stay tuned! 🖖

Morgan

@morganlinton

cto @boldmetrics, evals @vulcanbench / not an expert, endlessly curious

加入 January 2009

1K 正在關注 47K 粉絲

Morgan@morganlinton

2026.09.24 16:52

Update on my Opus 5.5 benchmark with @VulcanBench As many of you know, I don't get early access to these models, so I can only start benchmarking the day the model is released. It looks like something in my eval suite is being refused by Claude Code's safety classifier, and is then falling back on Opus 4.8. Looking into this more, reviewing the traces now. But likely going to be a bit longer for me to get the benchmarks out, stay tuned! 🖖