GLM-5.3 leads overall
Ahead on 2 of 2 benchmarks, averaging 12.5 points higher
Summarised from the 2 benchmarks both models were scored on; details in the charts below. A further 1 Elo/rating-scale benchmarks are left out of the average — their scale cannot be added to percentages.
GLM-4.7
智谱AI
Updates live with the mode filters below.
Best overall
GLM-5.3 · 738.60
Best single
GLM-5.3 · Creative Writing 2062.40
Modality coverage
GLM-4.7 · 1 modalities
Head to head
3
Benchmarks
0
Wins
3
Losses
-225.60
Average diff
Benchmark-by-benchmark comparison. Changing the thinking mode or tool filters updates the chart and table below.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Every model and runtime mode, benchmark by benchmark. Values are comparable along a row, not between different benchmarks.
3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GLM-4.7 | GLM-5.3 |
|---|---|---|
HLE 综合评估 | 42.80Thinking Enabled ｜ Tools | 62.50Thinking Level · High ｜ Tools |
GPQA Diamond 科学与综合推理 | 85.70Thinking Enabled | 90.91Thinking Level · High |
Creative Writing 写作和创作 | 1410.50Standard Mode | 2062.40Standard Mode |
Official list prices per model API, split by input and output. Unit: USD per 1M tokens.
Architecture, licensing and API modalities. "Not provided" means the field is missing from our database.
| Features & specs | GLM-4.7智谱AI | GLM-5.3智谱AI |
|---|---|---|
Core specsRelease | 2025-12-22 | 2026-08-14 |
Context length | 200K | 1M |
Total parameters | 358B | 744B |
Active parameters | 32B | 40B |
Max output length | 132,072 tokens | 128,000 tokens |
Architecture | MoE (mixture of experts) | MoE (mixture of experts) |
Runtime modes | 关闭扩展开启 | 最高低高 |
LicenseCode Open Source | Open Source · MIT License | Open Source · Apache 2.0 |
Weights Open Source | Open Source · MIT License | Not provided |
Licensing status | 免费商用授权 | Not provided |
Local deploymentWeights | Hugging Face | Hugging Face |
Source repo | GitHub | GitHub |
API modality supportText Input/Output | / | / |
ResourcesPaper / report | GLM-4.7: Advancing the Coding Capability | GLM-5: from Vibe Coding to Agentic Engineering |
GLM-5.3
智谱AI
