今天新增gemini-4IMAGE
LiveBench 更新：Argon 胜过 Terra，数据分析见长
Bindu Reddy 总结新版 LiveBench：Fable 5.1 与 Astra 领先，Argon 击败 Terra 且擅长数据分析，Google 首次压过开源阵营。
Bindu Reddy
@bindureddy13 小时前收录原推发布于 2026.10.28
Bindu Reddy @bindureddy原推发布于 2026.10.28
LiveBench finally reflects real-world performance - Fable 5.1 and Astra are on top - Opus 5.5, not far behind, excels at design - Argon beats Terra, good at data analysis - Google beats open-source for the first time - DeepSeek is the top open-source model
x.com/bindureddy/status/2115452599696830867采集于 2026.10.29 10:08