System record
GLM 5.3 / Claude Code, Max
Organization: Z.ai · base model: GLM 5.3
System and setup
| Model version | not reported |
|---|---|
| Software used to run the model | Claude Code, Max reasoning, 1M context |
| Software version | not reported |
| Tools available to the model | One H100 and ten hours for each base-model/target run; benchmark evaluator and decontamination checker |
| Release date | Not reported |
Autonomy assessments
No autonomy assessment is published for this system.
Published capability results
| Measure | Version | Reported result | Date |
|---|---|---|---|
| PostTrainBench | PostTrainBench v1.2 · September 30 release | 34.52% | 2026-09-30 |
Related research
Additional system details
- System ID
- ptb-v12-glm-5-3
- Organization
- Z.ai
- Base model
- GLM 5.3
- Release date
- Not reported
- Assessment records
- 0
- Recursive evidence records
- 0