GLM 5.3 vs GLM 5V Turbo
| Benchmark | GLM 5.3 | GLM 5V Turbo |
|---|---|---|
| Humanity's Last Exam | 36.6 | 17.1 |
| Terminal-Bench 4.0 | 34.8 | — |
| AutomationBench-AA | 52 | — |
| MMMU-Pro (vision) | — | 72.8 |
Specs
| Spec | GLM 5.3 | GLM 5V Turbo |
|---|---|---|
| Input, per 1M | !$1.40 | $1.20 |
| Output, per 1M | !$4.40 | $4 |
| Cost per task? | $0.85 | — |
| Speed, tok/s | 92 | — |
| Context | 1M | 203K |
| Weights | Open | Closed |
| Released | Aug 2026 | Apr 2026 |
| Memory (4-bit) | 452 GB | — |
| Licence | glm-5.3 | — |
| Commercial use | Restricted | — |
| See images | — | ✓ |
| Read PDFs | — | Partial |
| Hear audio | — | — |
| Watch video | — | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | — | Partial |
| Return strict JSON | ✓ | Partial |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
GLM 5.3 → GLM 5V Turbo
Context: 1M → 203K
GLM 5V Turbo → GLM 5.3
No image input
Reasoning cannot be disabled›
Disabling reasoning is unsupported; keep reasoning enabled.
tool_choice auto · Z.ai API›
The first-party chat reference exposes only auto for tool_choice.
Complete unmodified reasoning_content›
Preserved thinking defaults on for Coding Plan and off for the standard API; when enabled, return complete unmodified reasoning_content in its original order to protect quality and cache hits.
Only one stop word›
Only one stop word is supported, so do not rely on a list of alternative stop sequences.