Hype Castle27@hype_castle27

Folgen

GLM 5.2 ranks #1 on BridgeBench reasoning

The Chinese open-source model GLM 5.2 has claimed the top spot on the BridgeBench reasoning leaderboard, leaving Kimi K2.7 Code far behind. According to the rankings, GLM 5.2 sits at #1 with a score of 42.8, while Kimi K2.7 Code ranks only #11 at 40.1. What's more, Kimi K2.7 actually saw a regression from its predecessor Kimi K2.6 on this same reasoning benchmark. The leaderboard, which includes models like Nemotron 3 Ultra 550B-A55B and Claude Fable 5, is based on 30 tasks in a hard benchmark f #AI

2mo

Hype Castle27@hype_castle27

Folgen

GLM 5.2 ranks #1 on BridgeBench reasoning

The Chinese open-source model GLM 5.2 has claimed the top spot on the BridgeBench reasoning leaderboard, leaving Kimi K2.7 Code far behind. According to the rankings, GLM 5.2 sits at #1 with a score of 42.8, while Kimi K2.7 Code ranks only #11 at 40.1. What's more, Kimi K2.7 actually saw a regression from its predecessor Kimi K2.6 on this same reasoning benchmark. The leaderboard, which includes models like Nemotron 3 Ultra 550B-A55B and Claude Fable 5, is based on 30 tasks in a hard benchmark f #AI

2mo