网传 Anthropic Opus 5.5 基准测试成绩曝光

BridgeMind @bridgemindai原推发布于 2026.09.23

在 X 上打开原推

OPUS 5.5 BENCHMARKS JUST DROPPED. It beats Fable 5.1 and GPT 6 Astra across the board. Agentic coding, knowledge work, reasoning, computer use, visual recognition. Opus 5.5 leads every single one. At half the price of Fable 5.1. Anthropic finally shipped the model we have been begging for. Smart enough to lead the frontier and affordable enough to actually use. Testing it now.