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-5.2
智谱AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 综合评估 +9.8 / Relative gap: none clear
Relative edge: none clear / Relative gap: 综合评估 -9.8
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 · 77.61
Best single
GLM-5.2 · AIME 2026 99.20
Modality coverage
Inkling · 3 modalities
Head to head
6
Benchmarks
6
Wins
0
Losses
+6.88
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-5.2 | Inkling |
|---|---|---|
HLE 综合评估 | 54.70Thinking Enabled | Tools | 46.00Thinking Enabled | Tools |
GPQA Diamond 科学与综合推理 | 91.86Thinking Level · High | 87.20Thinking Enabled |
SWE-Bench Pro - Public 编程与软件工程 | 62.10Thinking Enabled | Tools | 54.30Thinking Enabled | Tools |
MCP-Atlas AI Agent - 工具使用 | 76.80Thinking Enabled | Tools | 76.00Thinking Level · Extra High | Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 81.00Thinking Level · High | Tools | 63.80Thinking Enabled | Tools |
AIME 2026 数学推理 | 99.20Thinking Enabled | 97.10Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GLM-5.2智谱AI | InklingThinking Machines Lab |
|---|---|---|
Core specsRelease | 2026-06-13 | 2026-07-15 |
Context length | 1M | 1M |
Parameters | 753.3B | 975B |
Active parameters | 40B | 41B |
Max output | 128000 | Not provided |
MoE | Yes | Yes |
Supported modes | No mode data | 常规模式(Non-Thinking Mode)可控思考强度(effort 0.2-0.99) |
LicenseCode Open Source | Open Source · MIT License | Open Source · Apache 2.0 |
Weights Open Source | Open Source · MIT License | Open Source · Apache 2.0 |
Commercial use | 免费商用授权 | 免费商用授权 |
Local deploymentWeight size | 约 1.5 TB(BF16 safetensors) | Not provided |
VRAM for weights | ≈ 1500 GB (weights only, excludes KV cache) | Not provided |
Weights | Hugging Face | Hugging Face |
Source repo | GitHub | Not provided |
Modality supportText Input/Output | / | / |
Image Input/Output | Not provided | / |
Audio Input/Output | Not provided | / |
ResourcesPaper / report | GLM-5: from Vibe Coding to Agentic Engineering | Not provided |
Inkling
Thinking Machines Lab