# /best-of-n does not run parallel model worktrees — falls back to single agent **URL:** \ **Category:** Bug Reports\ **Tags:** worktrees, chat\ **Created:** [April 2, 2026, 11:42pm UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550 "2026-04-02T23:42:52Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![danielcoder](https://avatars.discourse-cdn.com/v4/letter/d/58f4c7/32.png) [@danielcoder](https://forum.cursor.com/u/danielcoder)\ **Post date:** [April 2, 2026, 11:42pm UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/1 "2026-04-02T23:42:53Z")
### Where does the bug appear (feature/product)? Cursor IDE ### Describe the Bug /best-of-n runs as a single agent instead of spinning up parallel model worktrees. The specified model names are ignored and no comparison output is produced. ### Steps to Reproduce 1. Open a new agent chat in the Editor 2. Submit: /best-of-n gpt-5.4-high-fast, claude-4.6-opus-max-thinking 3. Observe only one agent runs - no worktrees created, no model comparison shown Note: /best-of-n also does not appear in slash command autocomplete ### Expected Behavior Per the this announcement ([Cursor 3: Worktrees & Best-of-N](https://forum.cursor.com/t/cursor-3-worktrees-best-of-n/156507)) /best-of-n should run the task across both models simultaneously, each in its own worktree, with a parent agent comparing results. ### Operating System MacOS ### Version Information Version: 3.0.4 (Universal) VSCode Version: 1.105.1 Commit: 63715ffc1807793ce209e935e5c3ab9b79fddc80 Date: 2026-04-02T09:36:23.265Z Build Type: Stable Release Track: Default Electron: 39.8.1 ### For AI issues: which model did you use? gpt-5.4-high-fast, claude-4.6-opus-max-thinking (Auto selected) ### For AI issues: add Request ID with privacy disabled be0d49ec-ee7d-472c-b645-c2f3a34aa166 ### Does this stop you from using Cursor No - Cursor works, but with this issue ---
**Author:** ![mohitjain](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/mohitjain/32/100229_2.png) [@mohitjain](https://forum.cursor.com/u/mohitjain)\ **Post date:** [April 3, 2026, 9:57am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/6 "2026-04-03T09:57:25Z")
Hey @danielcoder, This is a known limitation. The `/best-of-n` and `/worktree` slash commands are not yet available in the new Cursor 3 (Glass) interface — they only work in the classic editor mode. As a workaround for now, you can switch to the classic interface: go to **Cursor Settings \> General \> Interface** and select **Classic**. The `/best-of-n` command will work there. Alternatively, in the Glass interface, you can use the model picker UI to select multiple models (though this won’t create parallel worktrees like `/best-of-n` does). ---
**Author:** ![Vlad\_Tokarev](https://avatars.discourse-cdn.com/v4/letter/v/f19dbf/32.png) [@Vlad\_Tokarev](https://forum.cursor.com/u/Vlad_Tokarev)\ **Post date:** [April 6, 2026, 9:08am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/8 "2026-04-06T09:08:03Z")
For some reason, I’m seeing the selected model for all parallel agents instead of the relevant ones. “default” everywhere, instead of “gpt-54“, “opus46“, “composer2“. Classic UI ![image](https://us1.discourse-cdn.com/cursor1/original/3X/5/f/5ffe0c3fc2328173a358dff1be13d0b9bd5a504a.png) ---
**Author:** ![mohitjain](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/mohitjain/32/100229_2.png) [@mohitjain](https://forum.cursor.com/u/mohitjain)\ **Post date:** [April 6, 2026, 10:25am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/9 "2026-04-06T10:25:18Z")
Thanks for reporting this, and for the screenshot — helpful to see exactly what’s happening. This is a separate issue from the original report. The `/best-of-n` command is running and creating parallel agents, but the model names from your CSV aren’t being applied to each runner — they all fall back to “default” (Auto) instead of using the distinct models you specified. This is a known bug that our team is actively working on fixing. For now, the runners may all end up using the same auto-routed model rather than the specific ones you listed. ---
**Author:** ![kevglynn](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/kevglynn/32/83084_2.png) [@kevglynn](https://forum.cursor.com/u/kevglynn)\ **Post date:** [April 8, 2026, 4:48am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/11 "2026-04-08T04:48:38Z")
why did you deprecate/remove the multiple model toggle?!?!?!?! ☹ i want it back ☹ ---
**Author:** ![Thomas\_Levy](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/thomas_levy/32/104410_2.png) [@Thomas\_Levy](https://forum.cursor.com/u/Thomas_Levy)\ **Post date:** [April 10, 2026, 5:44pm UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/13 "2026-04-10T17:44:40Z")
I have been relying heavily on the multi-model interface/toggle and the /best-of-n, besides not working for using multiple models, also doesn’t seem to properly use other skills i reference in the prompt Altogether this feels like a pretty significant downgrade. The UI pre 3.0 was intuitive and functional ---
**Author:** ![mohitjain](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/mohitjain/32/100229_2.png) [@mohitjain](https://forum.cursor.com/u/mohitjain)\ **Post date:** [April 14, 2026, 7:06am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/15 "2026-04-14T07:06:39Z")
Following up on a few things in this thread. Model routing fix (update for @Vlad_Tokarev): The issue where all `/best-of-n` runners showed the same model (e.g., “default”) instead of the specified models should have been addressed in a recent update. If you’re still seeing this on the latest version, let me know, and I’ll dig in further. Multi-model toggle (@kevglynn, @Thomas_Levy ): The “Use Multiple Models” toggle has been moved. It’s now available when starting a new cloud (background) agent, rather than in the local editor or as a follow-up. This was an intentional change. There’s a related discussion in [Bring back the multiple models toggle](https://forum.cursor.com/t/bring-back-the-multiple-models-toggle-and-workflow-please/156993) if you’d like to add your voice there. Skills in `/best-of-n` (@Thomas_Levy): Could you share more details on what you mean by skills not being used properly? For example, are you referencing skills with `/skill-name` in your prompt, and the runners are ignoring them? A request ID from a session where this happened would help us investigate. ---
**Author:** ![Davide\_Carpini](https://avatars.discourse-cdn.com/v4/letter/d/ecb155/32.png) [@Davide\_Carpini](https://forum.cursor.com/u/Davide_Carpini)\ **Post date:** [April 17, 2026, 10:44pm UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/16 "2026-04-17T22:44:55Z")
Please, bring back the multiple models toggle locally!!! It was a game-changing feature, something I use every day to have multiple solutions on a single prompt, ex: UI interfaces. Best-of-n is not a replacement. ---
**Author:** ![Davide\_Carpini](https://avatars.discourse-cdn.com/v4/letter/d/ecb155/32.png) [@Davide\_Carpini](https://forum.cursor.com/u/Davide_Carpini)\ **Post date:** [April 24, 2026, 7:15am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/17 "2026-04-24T07:15:11Z")
you do updates almost every day, and on every update I hope to open the model section and see the multi-models feature back ---
**Author:** ![mohitjain](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/mohitjain/32/100229_2.png) [@mohitjain](https://forum.cursor.com/u/mohitjain)\ **Post date:** [April 24, 2026, 11:17am UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/19 "2026-04-24T11:17:09Z")
@Davide_Carpini - I hear you. The answer is the same as above — the multi-model toggle was intentionally moved to cloud (background) agents, and there’s no timeline for restoring it locally. The best place to track and voice support for that request is the [dedicated thread here](https://forum.cursor.com/t/bring-back-the-multiple-models-toggle-and-workflow-please/156993). ---
**Author:** ![system](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/system/32/99069_2.png) [@system](https://forum.cursor.com/u/system)\ **Post date:** [May 28, 2026, 2:13pm UTC](https://forum.cursor.com/t/best-of-n-does-not-run-parallel-model-worktrees-falls-back-to-single-agent/156550/22 "2026-05-28T14:13:09Z")
Closed on May 28, 2026, 2:13pm UTC This topic was automatically closed 22 days after the last reply. New replies are no longer allowed.