BREAKING
GLM-5.2 Hits No.10 on Agent Arena
0
Overall rank
0
Among open models
0
GLM-5.2 context
0
GLM-5.1 context
0
Max output
GLM-5.2 vs GLM-5.1
GLM-5.2
●
1M token context
●
High and Max modes
●
No benchmarks at launch
GLM-5.1
●
About 200K context
●
Single mode
●
SWE-Bench Pro published
0
$
Input per 1M
0
$
Output per 1M
0
B
MoE parameters
A Strong Open Coding Contender
AI NEWS BLITZ
Z.ai's GLM-5.2 just landed at number ten overall on the new Agent Arena leaderboard.