# GLM 5.3 Flash · Search Capability Leaderboard

* Search Intelligence Score: **60.8** (#18 in Search Intelligence)
* Without search: 20.4 · Lift from search +40.4
* Cost per 1K tasks: $16.6 (below the median score of 62.7, so not ranked on cost)
* Time per task: 99.1s
* Lab: Z.ai · Model id: z-ai/glm-5.3-flash

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 81.4        | 32.4           |
| HLE   | 36.0        | 22.0           |
| WISER | 65.0        | 7.0            |

## Compared with

| Model                                     | Score | Lift  | Cost per 1K tasks | Time per task |
| ----------------------------------------- | ----- | ----- | ----------------- | ------------- |
| GLM 5.3 Flash                             | 60.8  | +40.4 | $16.6             | 99.1s         |
| [GLM 5.3](/leaderboard/glm-5-3)           | 62.7  | +40.8 | $78.5             | 308s          |
| [GLM-5.2](/leaderboard/glm-5-2)           | 54.3  | +35.9 | $66.6             | 301s          |
| [GPT-5.6 Luna](/leaderboard/gpt-5-6-luna) | 60.7  | +33.9 | $36.2             | 98.0s         |
| [GPT-6 Luna](/leaderboard/gpt-6-luna)     | 61.9  | +33.9 | $33.1             | 391s          |

Latest update October 5, 2026\. Methodology: /leaderboard#methodology