Sara Kangaslahti

s-kangasl's activity

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

New activity in Harvard-DCML/boomerang-qwen3-4.9B 2 months ago

Substantially lower accuracy on reasoning benchmarks such as GSM8K (1.5%) and MATH-500 (4.2%)

1

#1 opened 3 months ago by

jonny-vr