Event ·Multi-source

Kimi K3.1 在 LiveBench 上跑分不及 DeepSeek Flash

Bindu Reddy 在 LiveBench 上对比了 Kimi K3.1 与 DeepSeek Flash 的成绩，Kimi K3.1 排名更低。她认为 Kimi K3.1 存在针对公开基准刷分的迹象，不过在单任务价格上仍具竞争力。她还提到 Kimi K3.1 与 Fable、Astra 级别的模型有差距，认为 DeepSeek 仍是开源模型中的领先者。

Current read

Moonshot 的 Kimi K3.1 在 LiveBench 上被 DeepSeek Flash 反超，还有刷分嫌疑，开源榜一还是 DeepSeek。

11 sources54° AI heatLast updated 2026/10/23 23:37:30

Evidence

11 sources

Primary sourceBindu Reddy

2026/10/23 23:37:30View source

Related source 1Yuchen Jin

2026/10/23 17:48:35View source

Related source 2SiliconFlowAI

2026/10/23 13:42:34View source

Related source 3TestingCatalog

2026/10/23 17:44:47View source

Related source 4Simon Willison’s Weblog

2026/10/23 19:40:54View source

Related source 5rohanpaul_ai

2026/10/23 15:32:59View source

Related source 6kimmonismus

2026/10/23 17:18:42View source

Related source 7IT之家

2026/10/23 23:08:43View source

Related source 8Artificial Analysis

2026/10/22 02:04:56View source

Related source 9Teortaxes

2026/10/22 14:00:18View source

Related source 10roon

2026/10/22 03:58:10View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story