# GLM 5.3 · Search Capability Leaderboard

* Search Intelligence Score: **55.3** (#8 in Search Intelligence)
* Without search: 20.0 · Lift from search +35.3
* Cost per 1K tasks: $110 (#5 in Search Efficiency)
* Time per task: 147s
* Lab: Z.ai · Model id: z-ai/glm-5.3-openrouter

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 44.0        | 7.0            |
| HLE   | 59.0        | 42.0           |
| WISER | 63.0        | 11.0           |

## Compared with

| Model                                             | Score | Lift  | Cost per 1K tasks | Time per task |
| ------------------------------------------------- | ----- | ----- | ----------------- | ------------- |
| GLM 5.3                                           | 55.3  | +35.3 | $110              | 147s          |
| [GLM-5.2](/leaderboard/glm-5-2)                   | 51.7  | +34.7 | $122              | 118s          |
| [GPT-5.6 Luna](/leaderboard/gpt-5-6-luna)         | 54.7  | +32.3 | $23.0             | 59.4s         |
| [Kimi K3](/leaderboard/kimi-k3)                   | 56.3  | +32.3 | $209              | 198s          |
| [Gemini 3.7 Flash](/leaderboard/gemini-3-7-flash) | 54.3  | +25.3 | $61.1             | 79.7s         |

Latest update September 14, 2026\. Methodology: /leaderboard#methodology