benchmarkIMAGE
Opus 5.5 基准测试几乎全面压过 GPT-6 Astra
泄露的基准图显示 Opus 5.5 在几乎所有评测项上超过 Fable 5.1，也几乎全部超过 GPT-6 Astra。
Chubby♨️
@kimmonismus2026.09.23收录原推发布于 2026.09.23
Chubby♨️ @kimmonismus原推发布于 2026.09.23
And here are the benchmarks! Opus 5.5 excels Fable 5.1 in literally every single eval and even GPT-6 Astra in almost every single one. Holy moly, this is going to be interesting! h/t @synthwavedd
这条是引用着另一条写的：x.com/kimmonismus/status/2102435059123056793
x.com/kimmonismus/status/2102435466348032027采集于 2026.09.23 10:28