# OpenRouter Auto (max) / Search Capability Leaderboard

* Search Intelligence Score: **67.7** (#21 in Search Intelligence)
* Without search: 37.7 / Lift from search +30.0
* Cost per 1K tasks: $116 (#5 in Search Efficiency)
* Evaluated: Nov 12, 2026
* Lab: OpenRouter / Weights: Closed / Model id: openrouter/auto

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 91.1        | 48.1           |
| HLE   | 47.0        | 47.0           |
| WISER | 65.0        | 18.0           |

## Compared with

| Model                                             | Score | Lift  | Cost per 1K tasks |
| ------------------------------------------------- | ----- | ----- | ----------------- |
| OpenRouter Auto (max)                             | 67.7  | +30.0 | $116              |
| [GPT-5.6 Sol](/leaderboard/gpt-5-6-sol)           | 67.7  | +26.3 | $269              |
| [Ember-1](/leaderboard/ember-1)                   | 67.9  | +38.0 | $335              |
| [Muse Spark Open](/leaderboard/muse-spark-open)   | 67.2  | +31.8 | $171              |
| [Gemini 3.7 Flash](/leaderboard/gemini-3-7-flash) | 66.8  | +27.4 | $130              |

Leaderboard last updated Nov 12, 2026. Methodology: /leaderboard#methodology