Fix AIME 2025 numeric scoring (equality, not suffix match)#45
Open
wise-east wants to merge 1 commit into
Open
Conversation
inspect_ai match(numeric=True) grades with endswith on the extracted answer, which marks predictions like 711 correct when the label is 11. Add a local scorer that parses ANSWER lines and compares normalized values with ==. Fixes aisa-group#44 Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
inspect_evals/aime2025(usesmatch(numeric=True)→endswithon extracted digits) with a local inspect task and scorer that grades via normalized equalityANSWER:line when present; fall back to last numeric token (same extraction intent as inspect)\boxed{}stripping with iterative non-greedy substitutionscore.py/task.pyinto job dir inrun_task.shFixes #44
Test plan
cd src/eval/tasks/aime2025 PYTHONPATH=. pytest test_score.py -qUpstream
Long-term fix belongs in
inspect_ai(_common.pynumeric +endshould use==). This PR mitigates PostTrainBench until inspect-ai is updated.Made with Cursor