BigCodeArena
🚀
39
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 • 41 -
bigcode/bigcodearena-raw-14k
Viewer • Updated • 14.1k • 58 • 2 -
bigcode/bigcodearena-preference-5k
Viewer • Updated • 4.73k • 862 • 1 -
bigcode/bigcodereward
Viewer • Updated • 4.73k • 1.19k • 2 -
bigcode/bigcodereward-experiment-results
Viewer • Updated • 141k • 266 -
bigcode/autocodearena-v0
Viewer • Updated • 600 • 114 • 3