GLM-4.5
deprecated
Zhipu AI2025-07-28
Specifications
Modalities
text
Context Window131K tokens
Max Output-
Training Cutoff-
Open SourceYes
Pricing (per 1M tokens)
Input$-
Output$-
Benchmarks
Arena score (text)1411
Arena ratings: LMArena leaderboard dataset, CC BY 4.0, snapshot 2026-10-28.
MMLU-Pro-
SWE-Bench-
GPQA Diamond-
HumanEval-
ARC-AGI-
MATH-
Sources
- Hugging Face: zai-org/GLM-4.5 model card
is open source
- arXiv: GLM-4.5: Agentic, Reasoning, and Coding Foundation Models
paper url
- LMArena: Arena leaderboard dataset, text_style_control overall: GLM-4.5
elo rating · as of 2026-10-28