zai-org/SWE-Dev-train
Viewer
•
Updated
•
20.1k
•
153
•
10
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 • 182 • 14 -
lmarena-ai/webdev-arena-preference-10k
Viewer • Updated • 10.5k • 133 • 14 -
SWE-bench/SWE-smith-trajectories
Viewer • Updated • 76k • 2.5k • 34 -
DigitalLearningGmbH/MATH-lighteval
Viewer • Updated • 25k • 17.7k • 54 -
agentica-org/DeepScaleR-Preview-Dataset
Viewer • Updated • 40.3k • 9.52k • 177 -
PRIME-RL/Eurus-2-RL-Data
Viewer • Updated • 483k • 1.18k • 48