Shashi
@Shashikant86
Founder @SuperagenticAI, ex-๏ฃฟ Apple. ๐ฏAgent Engineering & Agent experience. Agentic AI Event host London ๐ฌ๐ง SF ๐. Researching Quantum AI. Father to 2
๊ฐ์
January 2010
1.8K ํ๋ก์ ์ค 2.8K ํฌ
Terminal-bench is the best benchmark to measure the coding agent harnesses and glad to see that GLM-5.3 is at third spot right now.
Not going to take long for GLM team to grab number 1 ๐ฅspot there. Great work @ZixuanLi_ and entire @Zai_org team.
๋ ๋ณด๊ธฐ
Terminal-Bench 4.0 just dropped.
Benchmark iteration is catching up with model development.
