Matt Fisher

mrpfisher's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in openai/MMMLU 6 days ago

Translation collapses distinct MMLU questions into identical text with conflicting answers (FR_FR, IT_IT, AR_XY)

#18 opened 6 days ago by

mrpfisher

New activity in hicai-zju/SciKnowEval 6 days ago

v1 test split: 460 exact-duplicate rows, and 223 rows where an identical input has a different reference answer

#3 opened 6 days ago by

mrpfisher

New activity in BBEH/bbeh 6 days ago

Two identical rows in the spatial reasoning task (train rows 3185 and 3191)

#2 opened 6 days ago by

mrpfisher

published a Space 3 months ago

Running

Chess Bench Logs

📊

View chess benchmark logs in a clear web interface

New activity in FrontierCS/Frontier-CS 4 months ago

Add configs field to datacard

#3 opened 4 months ago by

mrpfisher

Dataset viewer times out (504) on split-name resolution and /is-valid reports all false

1

#2 opened 4 months ago by

mrpfisher