benchmarks: mirror the SHA-316 gate-v2 re-benchmark — published miss, new same-run numbers - #44
Merged
Merged
Conversation
… new same-run numbers Semantic section updated to the 2026-08-31 matrix (seekstone#299): quality mode 88.7% overall / 91.7% held-out beats tc's plain semantic on holdout; tc GraphRAG keeps #1 at 95.0% held-out with its costs stated; the pre-registered gate miss is linked clause-by-clause (GATE-V2-SHA-316.md). Stats cards move to the 150-query set (74% vs 18%, ~15 ms default model).
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Semantic section updated to the 2026-08-31 matrix (seekstone#299): quality
mode 88.7% overall / 91.7% held-out beats tc's plain semantic on holdout;
tc GraphRAG keeps #1 at 95.0% held-out with its costs stated; the
pre-registered gate miss is linked clause-by-clause (GATE-V2-SHA-316.md).
Stats cards move to the 150-query set (74% vs 18%, ~15 ms default model).