#15
GLM 5.3
glm-5.3Helpfulness
Instruction
Following
Comprehension
Empathy
Creative
Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 56 tok/s
Overall Assistant Score
An average score combining the 5 main categories.
91.40 pts
Rank #15
86th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
GLM 5.3 is Z.ai's August 2026 open flagship—same 743B GLM-5.2 base, with all gains from scaled post-training for coding agents, long-horizon work, and tool follow-through. Our assistant tests put it ahead of 5.2 on helpfulness, instruction following, and comprehension for messy multi-step help that has to finish. Empathy stays cool and professional. Creative writing is still utilitarian: clearer diffs than stories, so Fable and GPT-4.5 remain the prose picks. Best open model when you want an agent that keeps going; not the warmest chat partner. Same $1.40/$4.40 API rate as 5.2.
Overall Score vs Price
Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better
Ringed point is this model
Anthropic
Baidu
Bytedance
DeepSeek
Google
Meta
Minimax
Mistral
Moonshot
OpenAI
Qwen
SpaceX AI
Tencent
Xiaomi
Zhipu AI
Compare this model
Intelligence
Overall Score · Higher is better
Speed
Output tokens per second · Higher is better
Price
USD per 1M input tokens · Lower is better
Zhipu AI Models
Overall Score · Same provider
GLM Family
Overall Score · Same model family
Closest Rivals
Overall Score · Nearest by overall rank