# Beam · Search Capability Leaderboard

* Search Intelligence Score: **56.0** (#37 in Search Intelligence)
* Without search: 28.8 · Lift from search +27.2
* Cost per 1K tasks: $161 (below the median score of 63.5, so not ranked on cost)
* Time per task: —
* Lab: Reflection AI · Weights: Open weights · Model id: reflection/beam

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 68.9        | 38.4           |
| HLE   | 39.0        | 38.0           |
| WISER | 60.0        | 10.0           |

## Compared with

| Model                                                       | Score | Lift  | Cost per 1K tasks | Time per task |
| ----------------------------------------------------------- | ----- | ----- | ----------------- | ------------- |
| Beam                                                        | 56.0  | +27.2 | $161              | —             |
| [GLM-5.2](/leaderboard/glm-5-2)                             | 54.3  | +35.9 | $66.6             | 301s          |
| [Hunyuan 3](/leaderboard/hy3)                               | 58.2  | +35.6 | $28.4             | 363s          |
| [DeepSeek V4 Pro](/leaderboard/deepseek-v4-pro)             | 58.4  | +27.9 | $110              | 383s          |
| [DeepSeek V4 Pro (0813)](/leaderboard/deepseek-v4-pro-0813) | 53.5  | +20.4 | $234              | 394s          |

Latest update October 17, 2026\. Methodology: /leaderboard#methodology