THUDM/SWE-Dev-train
Viewer
•
Updated
•
20.1k
•
179
•
5
Agent tuning
Note Training traces that helped a 32B model achieve gpt-4o level performance on SWE-bench. OpenHands framework
-
SWE-Gym/OpenHands-SFT-Trajectories
Viewer • Updated • 491 • 215 • 9 -
lmarena-ai/webdev-arena-preference-10k
Viewer • Updated • 10.5k • 241 • 8 -
SWE-bench/SWE-smith-trajectories
Viewer • Updated • 5.02k • 1.15k • 16 -
DigitalLearningGmbH/MATH-lighteval
Viewer • Updated • 25k • 28.3k • 33