Repository navigation
Pi executor backend + SWE-bench Verified head-to-head - #2
Merged
Merged
Conversation
Runs the Pi coding agent in print/json mode in the run's worktree and sums token usage from its message_end events. Never auto-routed unless listed in policy routing. OPENSWARM_PI_BIN may point at a wrapper with the same flags.
…, MiniMax 2-arm subset)
This was referenced Oct 17, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds opt-in
--backend pi(pi -p --mode json, usage summed from message_end; tests in tests/test_pi.py).Real-task (SWE-bench Verified) head-to-head under
bench/swebench/, and a new top block in README.deepseek-flashvia Pi, all 4 arms on 6 instances, n=1 per cell: resolved baseline 1/6, superpowers 0/6, OpenFlow 2/6, openswarm 3/6. Median $ per task (DeepSeek list price) $0.023 / $0.029 / $0.041 / $0.038.