Event ·Multi-source

B站「AI无限竞技场」用真实场景评测大模型，GPT6-Astra登顶

B站发起「AI无限竞技场」活动，让UP主用真实任务测试AI模型。活动收录190个视频，测试包括代码编程、量化交易、3D建模等场景。投稿者多为模型评测高手，如牙医老师、oil欧呦。榜单前三名是GPT6-Astra、Fable 5.1、GLM-5.3。

Current read

B站搞了个「AI无限竞技场」，让UP主用真实任务测试AI模型，比如给个屎山代码项目让模型PK，或者让不同模型玩狼人杀。比那些刷分、炫技的评测靠谱多了。

11 sources58° AI heatLast updated 2026/9/20 03:31:25

Evidence

11 sources

Primary source向阳乔木

2026/9/20 03:31:25View source

Related source 1IT之家

2026/9/20 05:46:36View source

Related source 2宝玉的分享

2026/9/19 00:00:00View source

Related source 3Jerry Liu

2026/9/19 01:07:43View source

Related source 4Decoder

2026/9/19 13:28:55View source

Related source 5AI Will

2026/9/20 02:43:28View source

Related source 6宝玉

2026/9/20 03:20:28View source

Related source 7歸藏(guizang.ai)

2026/9/21 03:06:58View source

Related source 8eric zakariasson

2026/9/21 22:01:00View source

Related source 9shao__meng

2026/9/18 08:50:46View source

Related source 10@OpenAIDevs

2026/9/19 00:56:31View 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