33
BigCodeArena
🚀
Compare two AI models by sending them code and seeing their responses
⚔️ BigCodeArena
Unveiling More Reliable Human Preferences in Code Generation via Execution
-
-
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 32 -
bigcode/bigcodearena-raw-14k
Viewer • Updated • 14.1k • 71 • 1 -
bigcode/bigcodearena-preference-5k
Viewer • Updated • 4.73k • 69 -
bigcode/bigcodereward
Viewer • Updated • 4.73k • 175 • 1 -
bigcode/bigcodereward-experiment-results
Viewer • Updated • 141k • 112 -
bigcode/autocodearena-v0
Viewer • Updated • 600 • 142 • 2