# Muse Wonder 1.0 · Search Capability Leaderboard

* Search Intelligence Score: **71.3** (#5 in Search Intelligence)
* Without search: 35.3 · Lift from search +36.0
* Cost per 1K tasks: $709 (#17 in Search Efficiency)
* Time per task: 287s
* Lab: Meta · Model id: meta/muse-wonder-1.0

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 84.0        | 48.0           |
| HLE   | 54.0        | 46.0           |
| WISER | 76.0        | 12.0           |

## Compared with

| Model                                         | Score | Lift  | Cost per 1K tasks | Time per task |
| --------------------------------------------- | ----- | ----- | ----------------- | ------------- |
| Muse Wonder 1.0                               | 71.3  | +36.0 | $709              | 287s          |
| [Muse Spark 1.3](/leaderboard/muse-spark-1-3) | 66.1  | +35.8 | $142              | 274s          |
| [GPT-6 Astra](/leaderboard/gpt-6-astra)       | 70.8  | +27.9 | $401              | 83.7s         |
| [GPT-6.1 Sol](/leaderboard/gpt-6-1-sol)       | 70.4  | +30.6 | $130              | 353s          |
| [Pareto 26.9](/leaderboard/pareto-26-9)       | 72.5  | +32.8 | $184              | 211s          |

Latest update October 12, 2026\. Methodology: /leaderboard#methodology