Zhipu AI · Released Apr 18, 2026
GLM-5.3 (max)
Zhipu AI's high-speed frontier open-weights model combining high throughput with top-tier bilingual and agentic execution.
OpenRating Index
59.4
0–100 composite
Reasoning Index
81.8
0–100 composite
Cost / Task
$0.69
benchmark run
Output speed
95 tok/s
blended tok/s
Time to first token
0.7s
median latency
Input price
$0.75
per 1M tokens
Output price
$3
per 1M tokens
Context window
256K
tokens
Strengths
Impressive 95 tok/s output speed for frontier-tier model
Effective prompt caching economics reducing task cost
Comprehensive tool calling and function integration
How we rate GLM-5.3 (max)
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
59.4
Reasoning Index
81.8
Token Pricing
Input per 1M tokens
$0.75
Output per 1M tokens
$3
Cost of 1M input + 1M output
$3.75
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.69 total).
Related models
Compare GLM-5.3 (max) with the models it is most often measured against.