GLM 5.2 vs GLM 5.3
Different efforts: non-thinking · low · Compare all at max
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
GLM 5.2 · max1,454
GLM 5.3 · max1,453
EQ-Bench Longform Creative Writing 1.11 Longform Creative Writing 1.11: Models plan, revise and write a story across eight turns, graded with a writing rubric
GLM 5.277.9
GLM 5.381.8
EQ-Bench Creative Writing v3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking
GLM 5.21,756.5
GLM 5.32,075
Lech Mazur Short-Story Lech Mazur Short-Story · comparison score: Judges compare stories written to ten required elements; the comparison score can be negative
GLM 5.2 · max0.5
GLM 5.3 · max3
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions
GLM 5.2 · max73.3
GLM 5.3—
Harvey LAB-AA 1.1 Harvey LAB-AA 1.1: Legal agents work from case documents; every rubric criterion must pass and material hallucinations receive no credit
GLM 5.2—
GLM 5.3 · max0.3
| Benchmark | GLM 5.2 | GLM 5.3 |
|---|---|---|
| Arena Text · creative writing | 1,454 · max | 1,453 · max |
| EQ-Bench Longform Creative Writing 1.11 | 77.9 | 81.8 |
| EQ-Bench Creative Writing v3 | 1,756.5 | 2,075 |
| Lech Mazur Short-Story | 0.5 · max | 3 · max |
| IFBench (instructions) | 73.3 · max | — |
| Harvey LAB-AA 1.1 | — | 0.3 · max |
Specs
| Spec | GLM 5.2 | GLM 5.3 |
|---|---|---|
| Input, per 1M | !$1.40 | !$1.40 |
| Output, per 1M | !$4.40 | !$4.40 |
| Cost per task? | — | $0.85 |
| Speed, tok/s | 171 | 126 |
| Context | 1M | 1M |
| Weights | Open | Open |
| Released | Jun 2026 | Aug 2026 |
| Memory (4-bit) | 452 GB | 452 GB |
| Licence | MIT | glm-5.3 |
| Commercial use | Allowed | Restricted |
| See images | — | — |
| Read PDFs | — | — |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | — |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
GLM 5.2 → GLM 5.3
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.
GLM 5.3 → GLM 5.2
Nothing known.