GLM-5.2vsQwen3.7 Max
Across 8 shared benchmarks, GLM-5.2 leads overall: GLM-5.2 wins 6, Qwen3.7 Max wins 2, with 0 ties and an average score difference of +5.80.
GLM-5.2
智谱AI · 2026-06-13 · Reasoning model
Qwen3.7 Max
阿里巴巴 · 2026-05-20 · Reasoning model
GLM-5.26 wins(75%)(25%)2 winsQwen3.7 Max
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
Coding and Software Engineer
GLM-5.2 2/2| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| Text Arena (Coding) | 1,5935 / 35最高（无工具） | 1,54111 / 35Normal (No Tools) | +52.48 |
| SWE-Bench Pro - Public | 62.109 / 57Thinking (With Tools) | 60.6012 / 57Thinking (With Tools) | +1.50 |
General Knowledge
GLM-5.2 2/2| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| LiveBench | 76.249 / 115Normal (No Tools) | 74.2921 / 115Deep Thinking (No Tools) | +1.95 |
| HLE | 54.7015 / 181Thinking (With Tools) | 53.5018 / 181Thinking (With Tools) | +1.20 |
AI Agent - Tool Usage
GLM-5.2 1/1| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| MCP-Atlas | 76.8013 / 38Thinking (With Tools) | 76.4016 / 38Thinking (With Tools) | +0.40 |
Commonsense Reasoning
Qwen3.7 Max 1/1| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| SimpleBench | 58.8020 / 67Normal (No Tools) | 70.407 / 67Normal (No Tools) | -11.60 |
General Evaluation
Qwen3.7 Max 1/1| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| GPQA Diamond | 91.8626 / 226最高（无工具） | 92.4022 / 226最高（无工具） | -0.54 |
Math and Reasoning
GLM-5.2 1/1| Benchmark | GLM-5.2 | Qwen3.7 Max | Diff |
|---|---|---|---|
| IMO-AnswerBench | 912 / 23Thinking (No Tools) | 903 / 23最高（无工具） | +1 |
Specs
| Field | GLM-5.2 | Qwen3.7 Max |
|---|---|---|
| Publisher | 智谱AI | 阿里巴巴 |
| Release date | 2026-06-13 | 2026-05-20 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | Dense |
| Parameters | 753.33B | Not available |
| Context length | 1M | 1M |
| Max output | 128K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GLM-5.2 | Qwen3.7 Max |
|---|---|---|
| Text input | $1.4 / 1M tokens | ¥12 / 1M tokens |
| Text output | $4.4 / 1M tokens | ¥36 / 1M tokens |
| Cache read | $0.26 / 1M tokens | Not public |
Summary
- GLM-5.2leads in:Coding and Software Engineer (2/2), General Knowledge (2/2), AI Agent - Tool Usage (1/1), Math and Reasoning (1/1)
- Qwen3.7 Maxleads in:Commonsense Reasoning (1/1), General Evaluation (1/1)
On average across the 8 shared benchmarks, GLM-5.2 scores 5.80 higher.
Largest single-benchmark gap: Text Arena (Coding) — GLM-5.2 1,593 vs Qwen3.7 Max 1,541 (+52.48).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.