GLM-5.3
Z.ai's coding-model update, announced with post-training gains, three reasoning-effort levels, and publisher-reported coding and cyber benchmarks.
GLM-5.3 is available on MiniRouter as . The model page has current pricing, provider routes and API setup.
About the model
- Price: Not published. No API price is listed in the announcement
- Weights: Planned. Z.ai says weights will follow two weeks after launch
- Reasoning effort: low / high / max. Three publisher-described effort levels
- Base model: Same as GLM-5.2. Z.ai attributes the gains to post-training
Publisher pricing
Pricing below comes from the linked publisher sources and does not represent a MiniRouter route or price.
Not published
The publisher announcement does not list an API price. MiniRouter does not estimate one.
Publisher-reported benchmarks
Results from the publisher’s announcement, grouped by unit.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| Terminal Bench 3.0 | 28.3% | Z.ai | Aug 14, 2026 | Announcement ↗ |
| DeepSWE v1.1 | 66.9% | Z.ai | Aug 14, 2026 | Announcement ↗ |
| CyberGym | 84.5% | Z.ai | Aug 14, 2026 | Announcement ↗ |
| ExploitBench | 54.4% | Z.ai | Aug 14, 2026 | Announcement ↗ |
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| ExploitGym · 2 hours | 105 tasks | Z.ai | Aug 14, 2026 | Announcement ↗ |
| ExploitGym · 6 hours | 130 tasks | Z.ai | Aug 14, 2026 | Announcement ↗ |
Z.ai says GLM-5.3 uses the same base model as GLM-5.2 and attributes gains to post-training.
Z.ai reports the benchmark figures; MiniRouter has not reproduced them.
Independent measurements
Artificial Analysis evaluations of the first-party API.
GLM-5.3 (max) ranks #9 of 462 model families on their Intelligence Index.
- Intelligence Index
- 44.8
- Composite of their evaluations
- Coding Index
- 74.8
- Coding evaluations only
- Blended price
- $2.15
- USD per 1M tokens, 3:1 input to output, first-party list
- Output speed
- 69
- Median tokens per second
- First answer token
- 32s
- Median seconds, including reasoning
GLM-5.3 (max) on Artificial Analysis ↗
Source: Artificial Analysis ↗, read Sep 21, 2026. Measured on the model's first-party API, not a MiniRouter route.
Keep exploring
Compare published results in the model rankings and coding benchmarks, or read more model releases.
For MiniRouter product updates, visit the changelog.
Sources
- Read at Z.ai ↗
Z.ai announcement
Published Aug 14, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 21, 2026
Editorial reference revised 2026-09-29. Catalog status comes from the generated routing snapshot.