Z AI
GLM-5 (Non-reasoning)
GLM-5 is Zai’s new-generation flagship foundation model, designed for Agentic Engineering, capable of providing reliable productivity in complex system engineering and long-range Agent tasks. In terms of Coding and Agent capabilities, GLM-5 has achieved state-of-the-art (SOTA) performance in open source, with its usability in real programming scenarios approaching that of Claude Opus 4.5.
Z AI releasesModel Snapshot
TypeLanguage
ReleaseFeb 12, 2026
Context202,800
Tagsreasoning, tool-use, implicit-caching
Overall
Rank #73 across 526
40.6
Coding
Rank #59 across 436
39.0
Blended Price
Rank #235 across 357
$1.55/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed63.1 tok/s
First Token1.10s
Max Output131,100
Pricing
Blended$1.55/M
Input$1.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 40.6 | #73 |
| Artificial Analysis Coding Index | coding | 39.0 | #59 |
| GPQA | reasoning | 66.6% | #251 |
| Humanity's Last Exam | reasoning | 7.2% | #220 |
| SciCode |