Event ·Multi-source

LiveBench 榜单更新:Fable 5.1 与 Astra 登顶

LiveBench 排行榜更新后,Fable 5.1 和 Astra 位居前两名。Opus 5.5 紧随其后,在设计类任务上表现突出。Argon 的排名超过 Terra,数据分析是它的强项。Google 首次在榜单上超过了开源模型,DeepSeek 则是最强的开源模型。

Current read

LiveBench 排名更新了,Fable 5.1 和 Astra 冲到前两名,DeepSeek 守住开源第一,选模型前可以看看这份榜。

11 sources44° AI heatLast updated 2026/10/28 14:36:17

Evidence

11 sources
Primary sourceBindu Reddy
View source
Related source 1@koltregaskes
View source
Related source 2Shubham Saboo
View source
Related source 3Yuchen Jin
View source
Related source 4TestingCatalog
View source
Related source 5The Rundown AI
View source
Related source 6Artificial Analysis
View source
Related source 7rohanpaul_ai
View source
Related source 8kimmonismus
View source
Related source 10量子位
View 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.