# GLM-4.5 Benchmark Scores & Performance

> GLM-4.5 by Z.AI has 4 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/glm-4-5

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Z.AI |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | 128K |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: GLM-4.5
- Variant: base
- Benchmarks covered: 4 of 639
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 67.4% | [Vals AI: LiveCodeBench leaderboard](https://www.vals.ai/models/zai_glm-4.5) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Design Arena Website](/benchmarks/designarenawebsite) | 1171 | [OpenRouter model benchmarks](https://openrouter.ai/z-ai/glm-4.5/benchmarks) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA Diamond (Vals)](/benchmarks/gpqa-diamond) | 72.2% | [Vals AI: GPQA Diamond leaderboard](https://www.vals.ai/models/zai_glm-4.5) |
| [MMLU-Pro (Vals)](/benchmarks/mmlu-pro) | 81.2% | [Vals AI: MMLU Pro leaderboard](https://www.vals.ai/models/zai_glm-4.5) |

## Other Z.AI Models

- [GLM-5.3](/models/glm-5-3) - Score: 67.88
- [GLM-5.2](/models/glm-5-2) - Score: 60.5
- [GLM-5.3-Flash](/models/glm-5-3-flash) - Score: 58.52
- [GLM-5.1](/models/glm-5-1) - Score: 56.31
- [GLM-5](/models/glm-5) - Score: 54.84
- [GLM-5-Turbo](/models/glm-5-turbo) - Score: 53.19
- [GLM-5V-Turbo](/models/glm-5v-turbo) - Score: 49.6
- [GLM-4.7](/models/glm-4-7) - Score: 48.85
- [GLM-4.6](/models/glm-4-6) - Score: 40.02
- [GLM-4.7-Flash](/models/glm-4-7-flash) - Score: 39.13
- [GLM-4.5-Air](/models/glm-4-5-air) - Score: 34.93
- [GLM-5 (Reasoning)](/models/glm-5-reasoning) - Score: not computed