# GPT-6.1 Sol / Search Capability Leaderboard

* Search Intelligence Score: **70.4** (#9 in Search Intelligence)
* Without search: 39.8 / Lift from search +30.6
* Cost per 1K tasks: $130 (#7 in Search Efficiency)
* Evaluated: Sep 30, 2026
* Lab: OpenAI / Weights: Closed / Model id: gpt-6.1-sol

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 87.1        | 53.4           |
| HLE   | 48.0        | 45.0           |
| WISER | 76.0        | 21.0           |

## Compared with

| Model                                       | Score | Lift  | Cost per 1K tasks |
| ------------------------------------------- | ----- | ----- | ----------------- |
| GPT-6.1 Sol                                 | 70.4  | +30.6 | $130              |
| [GPT-6 Astra](/leaderboard/gpt-6-astra)     | 70.8  | +27.9 | $401              |
| [GPT-6.1 Terra](/leaderboard/gpt-6-1-terra) | 69.7  | +41.2 | —                 |
| [GPT-5.6 Sol](/leaderboard/gpt-5-6-sol)     | 67.7  | +26.3 | $269              |
| [GPT-6 Sol](/leaderboard/gpt-6-sol)         | 66.6  | +28.7 | $183              |

Leaderboard last updated Oct 31, 2026. Methodology: /leaderboard#methodology
