Zareian 5d490edaf9 keep the raw benchmark answers so the report's questions and answers never need re-running ...

102 unique textbook questions, 1,287 full model answers, per-answer cost and
the hand grades for both rounds. Book excerpts (retrieval context) are left out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-09-26 10:43:43 +03:30

..

benchmarks/2026-09-26-tutor-model

keep the raw benchmark answers so the report's questions and answers never need re-running

2026-09-26 10:43:43 +03:30

frontend

make every grade's id its class number and sort grades by it everywhere

2026-09-23 22:47:02 +03:30

architecture.md

record the v6 fraction-wording experiment: notation slightly better, answers slightly worse, not shipped

2026-09-26 03:25:43 +03:30

content-authoring.md

make every grade's id its class number and sort grades by it everywhere

2026-09-23 22:47:02 +03:30

docker.md

make the README an entry point and move procedures into docs/

2026-09-23 01:12:04 +03:30

extraction-playbook.md

complete the quiz path for grades 8 through 12, and close three gaps in the API contract

2026-09-22 03:49:32 +03:30

operations.md

list everything left open for the demo that must be closed before real users

2026-09-25 10:32:36 +03:30

security-before-production.md

record the live integration check: GapGPT back, Zarinpal -14 domain mismatch, Bazaar unset, test user 18

2026-09-25 18:48:57 +03:30