模型发布VIDEO
Inception Mercury 3 发布：1000+ tokens/秒，对比 Claude Code
Inception 发布最快模型 Mercury 3，在 Nvidia 硬件上超过 1000 tokens/秒，并用多子 agent 并行编码任务与 Claude Code + Sonnet 5.5 做对比演示。
Inception
@_inception_ai9 天前收录原推发布于 2026.10.21
Inception @_inception_ai原推发布于 2026.10.21
Yesterday, we launched Mercury 3, our fastest model to date with speeds over 1000+ tokens/second on @nvidia hardware. In this demo from @stefan_webb, we compare Mercury 3 + @opencode against Claude Code with Sonnet 5.5 and other model/harness combinations on a coding task utilizing many subagents running in parallel. (🧵1/2)
x.com/_inception_ai/status/2112588104955773059采集于 2026.10.21 10:21