Zhipu AI
•
Listed July 2025
•
Open Weights
GLM-4.5
Arena #148 • score 1411 ±5
Open Weights model from Zhipu AI, listed July 2025. Arena text score 1411 (#148 of 414 entries). $0.60 input / $2.20 output per 1M tokens. 128K tokens context.
Parameters
355B total, 32B active (MoE)
Context Window
128K tokens
Input / 1M tokens
$0.60
Output / 1M tokens
$2.20
Benchmark Results
- Arena Text Elo: 1411 (#148 of 414 on arena.ai · ±5 · 23,803 votes · variant: glm-4.5)
- SWE-bench Verified: 54.2% (mini-SWE-agent (bash only) · run 'GLM 4.5 (2025-08-22)' · 2025-08-22)
- AA Intelligence Index: 12.8 (Artificial Analysis v4.3 · best setting: GLM-4.5 (Reasoning) · checked 2026-10-11)