docs(benchmarks): BASELINES re-measured 2026-07-10 — task 9 done#96
Merged
Merged
Conversation
…MEASURE banner Full-25 benchmark run, task 9 of specs/rag-gate-accuracy-baseline, against the refreshed ground truth + regenerated templates (#95): sonnet treated 24/24 correct, opus treated 25/25, zero hallucinations, McNemar p ~ 0.0000, zero regressions. Top-line table reproduces the superseded v0.3.9 numbers exactly (incl. the q30 judge flake); header bumped to v0.25.0. contexts.json refreshed by the run.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Closes the last task of specs/rag-gate-accuracy-baseline: the full-25 benchmark ran against the refreshed ground truth and the freshly regenerated templates (#95).
Results: sonnet treated 24/24 correct (†q30 judge flake, same as v0.3.9), opus treated 25/25, zero hallucinations, McNemar p ≈ 0.0000 both models, zero regressions. Top-line table reproduces the superseded v0.3.9 numbers exactly — the ground-truth refresh moved per-question grading without shifting the aggregate gates, so the 95%/85% thresholds in eval_config.yaml remain correctly grounded.
Changes: PENDING RE-MEASURE banner dropped, header bumped to v0.25.0, post-regen smoke numbers recorded, contexts.json refreshed by the run.
🤖 Generated with Claude Code