GLM-5.2vsGLM 5.1
Across 6 shared benchmarks, GLM-5.2 leads overall: GLM-5.2 wins 6, GLM 5.1 wins 0, with 0 ties and an average score difference of +7.42.
GLM-5.26 wins(100%)(0%)0 winsGLM 5.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
General Knowledge
GLM-5.2 2/2| Benchmark | GLM-5.2 | GLM 5.1 | Diff |
|---|---|---|---|
| GPQA Diamond | 91.2015 / 179Thinking (No Tools) | 86.2043 / 179Thinking (No Tools) | +5 |
| HLE | 54.708 / 159Thinking (With Tools) | 52.3013 / 159Thinking (With Tools) | +2.40 |
Math and Reasoning
GLM-5.2 2/2| Benchmark | GLM-5.2 | GLM 5.1 | Diff |
|---|---|---|---|
| IMO-AnswerBench | 911 / 20Thinking (No Tools) | 83.8011 / 20Thinking (No Tools) | +7.20 |
| AIME 2026 | 99.201 / 15Thinking (No Tools) | 95.303 / 15Thinking (No Tools) | +3.90 |
AI Agent - Tool Usage
GLM-5.2 1/1| Benchmark | GLM-5.2 | GLM 5.1 | Diff |
|---|---|---|---|
| TerminalBench 2.1 | 814 / 14Thinking High (With Tools) | 58.7012 / 14Thinking High (With Tools) | +22.30 |
Coding and Software Engineer
GLM-5.2 1/1| Benchmark | GLM-5.2 | GLM 5.1 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 62.105 / 44Thinking (With Tools) | 58.4010 / 44Thinking (With Tools) | +3.70 |
Specs
| Field | GLM-5.2 | GLM 5.1 |
|---|---|---|
| Publisher | 智谱AI | 智谱AI |
| Release date | 2026-06-13 | 2026-03-27 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 753.33B | 75.4B |
| Context length | 1M | 200K |
| Max output | 128K | 125K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GLM-5.2 | GLM 5.1 |
|---|---|---|
| Text input | $1.4 / 1M tokens | $1.4 / 1M tokens |
| Text output | $4.4 / 1M tokens | $4.4 / 1M tokens |
| Cache read | $0.26 / 1M tokens | $4.4 / 1M tokens |
| Cache write | Not public | $0.26 / 1M tokens |
Summary
- GLM-5.2leads in:General Knowledge (2/2), Math and Reasoning (2/2), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1)
On average across the 6 shared benchmarks, GLM-5.2 scores 7.42 higher.
Largest single-benchmark gap: TerminalBench 2.1 — GLM-5.2 81 vs GLM 5.1 58.70 (+22.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.