Zhipu AI
•
Listed September 2025
•
Open Weights
GLM-4.6
Arena #124 • score 1424 ±4
Open Weights model from Zhipu AI, listed September 2025. Arena text score 1424 (#124 of 414 entries). $0.50 input / $2.00 output per 1M tokens. 205K tokens context.
Parameters
355B total, 32B active (MoE)
Context Window
205K tokens
Input / 1M tokens
$0.50
Output / 1M tokens
$2.00
Benchmark Results
- Arena Text Elo: 1424 (#124 of 414 on arena.ai · ±4 · 35,828 votes · variant: glm-4.6)
- SWE-bench Verified: 55.4% (mini-SWE-agent (bash only) · run 'GLM 4.6 (T=1)' · 2025-12-01)
- AA Intelligence Index: 18.5 (Artificial Analysis v4.3 · best setting: GLM-4.6 (Reasoning) · checked 2026-10-11)
- AA Coding Index: 45.8 (Artificial Analysis v4.3 · best setting: GLM-4.6 (Reasoning) · checked 2026-10-11)