Updated bench README.md

Cleaned old scans tests and removed [] and other symbols.
This commit is contained in:
Aman Rangapur 2025-04-23 13:53:24 -07:00 committed by GitHub
parent 7d8e9d181a
commit 85b40f46ce
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -105,7 +105,7 @@ Several categories of tests have been made so far:
- [ ] Review math equations in old_scans_math.jsonl using chat gpt script - [ ] Review math equations in old_scans_math.jsonl using chat gpt script
- [X] Add test category of long_texts which are still ~1 standard printed page, but with dense/small text - [X] Add test category of long_texts which are still ~1 standard printed page, but with dense/small text
- [ ] Review multicolumn_tests, make sure they are correct, clean, and don't have order tests between regions - [ ] Review multicolumn_tests, make sure they are correct, clean, and don't have order tests between regions
- [ ] Remove [] and other special symbols from old_scans - [X] Remove [] and other special symbols from old_scans
- [ ] Full review of old_scans, somehow, chatgpt or prolific - [ ] Full review of old_scans, somehow, chatgpt or prolific
- [ ] Adjust scoring to weight each test category equally in final score distribution - [ ] Adjust scoring to weight each test category equally in final score distribution
- [ ] Double check marker inline math outputs - [ ] Double check marker inline math outputs