GLM 5.1vsGLM-4.7
Across 6 shared benchmarks, GLM 5.1 leads overall: GLM 5.1 wins 6, GLM-4.7 wins 0, with 0 ties and an average score difference of +13.33.
GLM 5.16 wins(100%)(0%)0 winsGLM-4.7
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
General Knowledge
GLM 5.1 2/2| Benchmark | GLM 5.1 | GLM-4.7 | Diff |
|---|---|---|---|
| HLE | 52.3012 / 157Thinking (With Tools) | 42.8041 / 157 | +9.50 |
| GPQA Diamond | 86.2042 / 178Thinking (No Tools) | 85.7044 / 178 | +0.50 |
AI Agent - Information Search
GLM 5.1 1/1| Benchmark | GLM 5.1 | GLM-4.7 | Diff |
|---|---|---|---|
| BrowseComp | 79.3013 / 45Thinking (With Tools + Internet) | 5234 / 45 | +27.30 |
AI Agent - Tool Usage
GLM 5.1 1/1| Benchmark | GLM 5.1 | GLM-4.7 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 63.5013 / 46Thinking (With Tools) | 4143 / 46 | +22.50 |
Coding and Software Engineer
GLM 5.1 1/1| Benchmark | GLM 5.1 | GLM-4.7 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 58.409 / 43Thinking (With Tools) | 40.6039 / 43 | +17.80 |
Math and Reasoning
GLM 5.1 1/1| Benchmark | GLM 5.1 | GLM-4.7 | Diff |
|---|---|---|---|
| AIME 2026 | 95.302 / 14Thinking (No Tools) | 92.906 / 14 | +2.40 |
Specs
| Field | GLM 5.1 | GLM-4.7 |
|---|---|---|
| Publisher | 智谱AI | 智谱AI |
| Release date | 2026-03-27 | 2025-12-22 |
| Model type | Reasoning model | Chat model |
| Architecture | MoE | MoE |
| Parameters | 75.4B | 358B |
| Context length | 200K | 200K |
| Max output | 125K | 132072 |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GLM 5.1 | GLM-4.7 |
|---|---|---|
| Text input | $1.4 / 1M tokens | Not public |
| Text output | $4.4 / 1M tokens | Not public |
| Cache read | $4.4 / 1M tokens | Not public |
| Cache write | $0.26 / 1M tokens | Not public |
One or both models have incomplete public pricing.
Summary
- GLM 5.1leads in:General Knowledge (2/2), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), Math and Reasoning (1/1)
On average across the 6 shared benchmarks, GLM 5.1 scores 13.33 higher.
Largest single-benchmark gap: BrowseComp — GLM 5.1 79.30 vs GLM-4.7 52 (+27.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.