GLM-5.3vsGLM-5
Across 3 shared benchmarks, GLM-5.3 leads overall: GLM-5.3 wins 3, GLM-5 wins 0, with 0 ties and an average score difference of +160.60.
GLM-5.33 wins(100%)(0%)0 winsGLM-5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.
General Evaluation
GLM-5.3 1/1| Benchmark | GLM-5.3 | GLM-5 | Diff |
|---|---|---|---|
| GPQA Diamond | 90.9137 / 270最高（无工具） | 8691 / 270Thinking (No Tools) | +4.91 |
General Knowledge
GLM-5.3 1/1| Benchmark | GLM-5.3 | GLM-5 | Diff |
|---|---|---|---|
| HLE | 62.503 / 185Max (With Tools) | 50.4029 / 185Thinking (With Tools) | +12.10 |
Writing and Creative Capabilities
GLM-5.3 1/1| Benchmark | GLM-5.3 | GLM-5 | Diff |
|---|---|---|---|
| Creative Writing | 2,0623 / 99Normal (No Tools) | 1,59835 / 99Normal (No Tools) | +464.80 |
Specs
| Field | GLM-5.3 | GLM-5 |
|---|---|---|
| Publisher | 智谱AI | 智谱AI |
| Release date | 2026-08-14 | 2026-02-11 |
| Model type | Reasoning model | Chat model |
| Architecture | MoE | MoE |
| Parameters | 744B | 744B |
| Context length | 1M | 200K |
| Max output | 128K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GLM-5.3 | GLM-5 |
|---|---|---|
| Text input | $1.4 / 1M tokens | $1 / 1M tokens |
| Text output | $4.4 / 1M tokens | $3.2 / 1M tokens |
| Cache read | $0.26 / 1M tokens | Not public |
| Cache write | Not public | $0.2 / 1M tokens |
Summary
- GLM-5.3leads in:General Evaluation (1/1), General Knowledge (1/1), Writing and Creative Capabilities (1/1)
On average across the 3 shared benchmarks, GLM-5.3 scores 160.60 higher.
Largest single-benchmark gap: Creative Writing — GLM-5.3 2,062 vs GLM-5 1,598 (+464.80).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.