Data points: 72
The readout for GLM-4.7 and GLM-5.1, before the detailed comparison sheet.
Decision read
GLM-5.1
GLM-5.1 currently has the stronger profile, with verified wins split 1 to 4.
Evidence depth
72 data points
Includes 8 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with GLM-5.1
The charts below split 16 high-signal samples across speed, scores, and audit health.
Model compare GLM-4.7 vs GLM-5.1glm-4-7-vs-glm-5-1 | Model A GLM-4.7 | Model B GLM-5.1 |
|---|---|---|
| Overall leader | Contender | Leading |
| Verified metric wins | 1 wins | 4 wins |
| Where it leads | Average speed | First-token latency, Free providers, Provider coverage, Recent tests |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | GLM-4.7 | GLM-5.1 |
|---|---|---|
| HLE | 25.1%#30 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GLM-4.7 | GLM-5.1 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GLM-4.7 | GLM-5.1 |
|---|---|---|
75 tests | GLM-4.7 speed / latency 42 tok/s / 24443ms input / output No data |
This report only uses LMSpeed data for GLM-4.7 and GLM-5.1: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GLM-4.7 | GLM-5.1 |
|---|---|---|
| When to choose each model | GLM-4.7 GLM-4.7 is stronger when you prioritize Average speed. | GLM-5.1 GLM-5.1 is stronger when you prioritize First-token latency, Free providers, Provider coverage, Recent tests. |
TL;DR: GLM-5.1 leads across 72 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GLM-4.7 vs GLM-5.1 into nearby model comparisons with enough verified LMSpeed data.
| Model metadata | GLM-4.7 exposes 202.8K tokens; notable signals: Text input, Text output, Tool calling, Structured outputs. | No OpenRouter metadata is available yet for this model. |
|---|---|---|
| Developer | No data | Zhipu AI |
| Context window | 202.8K tokens | No data |
| Max output | 131.1K tokens | No data |
| Released | Dec 2025 | No data |
| Modalities | Input Text Output Text | No data |
| Features | Text inputText outputTool callingStructured outputsJSON modeReasoning | None listed |
| Parameters | No data | No data |
| Tokenizer | Other | No data |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | z-ai/glm-4.7 | No data |
| References | No data | No data |
| GPQA | 85.9%#27 | 86.8%#22 |
|---|
| SciCode | 45.1%#22 | 43.8%#26 |
|---|
| Input price | $0.600/M#23 | $1.40/M#32 |
|---|
| Output price | $2.20/M#25 | $4.40/M#33 |
|---|
| Time to first token | 0.86 s#28 | 0.90 s#31 |
|---|
| Blended price | $1.00/M#38 | $2.15/M#53 |
|---|
| Output speed | 107.0 tok/s#45 | 71.0 tok/s#72 |
|---|
GLM-5.1
speed / latency
35 tok/s / 17508ms
input / output
No data
火山引擎 Ark59 tests | GLM-4.7 speed / latency 39 tok/s / 28124ms input / output No data | GLM-5.1 speed / latency 35 tok/s / 22863ms input / output No data |
|---|
SiliconFlow45 tests | GLM-4.7 speed / latency 64 tok/s / 16663ms input / output No data | GLM-5.1 speed / latency 50 tok/s / 9040ms input / output No data |
|---|
Mars HK15 tests | GLM-4.7 speed / latency 134 tok/s / 1161ms input / output No data | GLM-5.1 speed / latency N/A / N/A input / output No data |
|---|
Ollama15 tests | GLM-4.7 speed / latency N/A / N/A input / output No data | GLM-5.1 speed / latency 62 tok/s / 25980ms input / output No data |
|---|
GLM-4.7 glm-4.7 speed / latency No data input / output $0.270/M / $1.10/M | GLM-5.1 glm-5.1 speed / latency No data input / output $0/M / $0/M |
GLM-4.7 ZhipuAI/GLM-4.7 speed / latency No data input / output $75.00/M / $75.00/M | GLM-5.1 GLM-5.1 speed / latency No data input / output $0/M / $0/M |
GLM-4.7 glm-4.7 speed / latency No data input / output $0/M / $0/M | GLM-5.1 glm-5.1-chat speed / latency No data input / output $0/M / $0/M |
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
