See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
GLM-5
智谱AI
GLM-5.2
智谱AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 数学推理 -7.5
Relative edge: 数学推理 +7.5 / Relative gap: none clear
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
GLM-5.2 · 78.63
Best single
GLM-5.2 · AIME 2026 99.20
Modality coverage
GLM-5 · 1 modalities
Head to head
6
Benchmarks
0
Wins
6
Losses
-6.36
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
6 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GLM-5 | GLM-5.2 |
|---|---|---|
HLE 综合评估 | 50.40Thinking Enabled ｜ Tools | 54.70Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 68.85Standard Mode | 76.24Standard Mode |
GPQA Diamond 科学与综合推理 | 86.00Thinking Enabled | 91.86Thinking Level · High |
SimpleBench 常识推理 | 53.20Standard Mode | 58.80Standard Mode |
AIME 2026 数学推理 | 92.70Thinking Enabled | 99.20Thinking Enabled |
IMO-AnswerBench 数学推理 | 82.50Thinking Enabled | 91.00Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GLM-5智谱AI | GLM-5.2智谱AI |
|---|---|---|
Core specsRelease | 2026-02-11 | 2026-06-13 |
Context length | 200K | 1M |
Parameters | 744B | 753.3B |
Active parameters | 40B | 40B |
Max output | 131072 | 128000 |
MoE | Yes | Yes |
LicenseCode Open Source | Open Source · Apache 2.0 | Open Source · MIT License |
Weights Open Source | Open Source · MIT License | Open Source · MIT License |
Commercial use | 免费商用授权 | 免费商用授权 |
Local deploymentWeight size | 1.51TB | 约 1.5 TB（BF16 safetensors） |
VRAM for weights | ≈ 1510 GB (weights only, excludes KV cache) | ≈ 1500 GB (weights only, excludes KV cache) |
Weights | Hugging Face | Hugging Face |
Source repo | GitHub | GitHub |
Modality supportText Input/Output | / | / |
ResourcesPaper / report | GLM-5: From Vibe Coding to Agentic Engineering | GLM-5: from Vibe Coding to Agentic Engineering |
