List your company

Code Execution Output Prediction on LiveCodeBench

90.92AccuracyVanilla
85.699287.054688.4189.7654Jun 1, 2026

Evaluation results

MethodLinks
VanillaModel=Qwen3-4B-Thinking-2507, Calibration Threshold Setup=calibrated on Bespoke-Stratos-17k without recalibration2026.0690.922,898
DEERModel=Qwen3-4B-Thinking-2507, Calibration Threshold Setup=calibrated on Bespoke-Stratos-17k without recalibration2026.0686.62,683
CUSUMModel=Qwen3-4B-Thinking-2507, Calibration Threshold Setup=calibrated on Bespoke-Stratos-17k without recalibration2026.0686.62,621
DynasorModel=Qwen3-4B-Thinking-2507, Calibration Threshold Setup=calibrated on Bespoke-Stratos-17k without recalibration2026.0685.92,596