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 5.1
智谱AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 常识推理 -11.7
Relative edge: 常识推理 +11.7 / 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
Qwen3.7 Max · 236.45
Best single
Qwen3.7 Max · Text Arena (Coding) 1540.77
Modality coverage
GLM 5.1 · 1 modalities
Head to head
9
Benchmarks
0
Wins
9
Losses
-5.04
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.
9 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GLM 5.1 | Qwen3.7 Max |
|---|---|---|
HLE 综合评估 | 52.30Thinking Enabled ｜ Tools | 53.50Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 70.18Standard Mode | 74.29Deep Thinking Mode |
GPQA Diamond 科学与综合推理 | 86.20Thinking Enabled | 92.40Thinking Level · High |
SimpleBench 常识推理 | 58.70Standard Mode | 70.40Standard Mode |
SWE-Bench Pro - Public 编程与软件工程 | 58.40Thinking Enabled ｜ Tools | 60.60Thinking Enabled ｜ Tools |
Text Arena (Coding) 编程与软件工程 | 1534.00Standard Mode | 1540.77Standard Mode |
MCP-Atlas AI Agent - 工具使用 | 75.60Standard Mode ｜ Tools | 76.40Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 63.50Thinking Enabled ｜ Tools | 69.70Thinking Enabled ｜ Tools |
IMO-AnswerBench 数学推理 | 83.80Thinking Enabled | 90.00Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GLM 5.1智谱AI | Qwen3.7 Max阿里巴巴 |
|---|---|---|
Core specsRelease | 2026-03-27 | 2026-05-20 |
Context length | 200K | 1M |
Parameters | 75.4B | — |
Active parameters | 4B | Not provided |
Max output | 128000 | 65536 |
MoE | Yes | No |
LicenseCode Open Source | Open Source · MIT License | Closed Source |
Weights Open Source | Open Source · MIT License | Closed Source |
Commercial use | 免费商用授权 | 不开源 |
Local deploymentWeight size | 1.51TB | Not provided |
VRAM for weights | ≈ 1510 GB (weights only, excludes KV cache) | Not provided |
Weights | Hugging Face | Not provided |
Source repo | GitHub | Not provided |
Modality supportText Input/Output | / | / |
ResourcesPaper / report | GLM-5.1: Towards Long-Horizon Tasks | Qwen3.7: The Agent Frontier |
Qwen3.7 Max
阿里巴巴
