gpt-6IMAGE

Moonshot claims Kimi K3.1 Pro wins 6 of 14 benchmarks vs US frontier models

Moonshot claims Kimi K3.1 Pro beats US frontier models on 6 of 14 benchmarks, priced at $2 input and $10 output per million tokens, about half Opus 5.5 and a fifth of GPT-6 Astra.

Ryan Orhan

@rynorhnArchived 5 days agoOriginally posted 2026.10.24

Moonshot claims Kimi K3.1 Pro wins 6 of 14 benchmarks vs US frontier models

Ryan Orhan @rynorhnOriginally posted 2026.10.24

Open original on X

i really wasn’t expecting a chinese lab to close the gap this aggressively right now. moonshot is claiming it beats every us frontier model in its comparison on 6 out of 14 benchmarks. and somehow they’re charging just $2 per million input tokens and $10 per million output tokens. opus 5.5 costs twice that. gpt-6 astra costs FIVE TIMES as much. what the fuck did moonshot cook 😭

This post quotes another post: x.com/rynorhn/status/2113685242766586208

x.com/rynorhn/status/2113686790150250526Archived 2026.10.24 10:09