# Qwen3.8 Max · Search Capability Leaderboard

* Search Intelligence Score: **66.0** (#20 in Search Intelligence)
* Without search: 28.9 · Lift from search +37.1
* Cost per 1K tasks: $221 (#13 in Search Efficiency)
* Evaluated: Oct 19, 2026
* Lab: Qwen · Weights: Closed · Model id: qwen/qwen3.8-max

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 88.1        | 38.7           |
| HLE   | 40.0        | 40.0           |
| WISER | 70.0        | 8.0            |

## Compared with

| Model                                           | Score | Lift  | Cost per 1K tasks |
| ----------------------------------------------- | ----- | ----- | ----------------- |
| Qwen3.8 Max                                     | 66.0  | +37.1 | $221              |
| [Grok 4.7 Medium](/leaderboard/grok-4-7)        | 66.0  | +44.8 | $252              |
| [Muse Spark 1.3](/leaderboard/muse-spark-1-3)   | 66.1  | +35.8 | $142              |
| [Claude Sonnet 5](/leaderboard/claude-sonnet-5) | 66.6  | +43.8 | $688              |
| [GPT-6 Sol](/leaderboard/gpt-6-sol)             | 66.6  | +28.7 | $183              |

Leaderboard last updated Oct 19, 2026. Methodology: /leaderboard#methodology