List your company

Code Generation on MBPP (pass@1, ∆3)

73.33Pass@1MURPHY - MARS
17.762832.188946.61561.0411Nov 11, 2025

Evaluation results

MethodLinks
MURPHY - MARSBackbone=Qwen3-4B, Rollouts=72, Iterations=32025.1173.332.4
GRPOBackbone=Qwen3-4B, Rollouts=72, Iterations=32025.1172.871.94
BaseBackbone=Qwen3-4B, Iterations=32025.1170.93—
MURPHY - MARSBackbone=Qwen3-1.7B, Rollouts=72, Iterations=32025.11628.07
GRPOBackbone=Qwen3-1.7B, Rollouts=72, Iterations=32025.1157.23.27
BaseBackbone=Qwen3-1.7B, Iterations=32025.1153.93—
MURPHY - MARSBackbone=Qwen3-4B, Rollouts=72, Iterations=12025.1153.33—
BaseBackbone=Qwen3-4B, Iterations=12025.1152.13—
GRPOBackbone=Qwen3-4B, Rollouts=72, Iterations=12025.1151.73—
GRPOBackbone=Qwen3-1.7B, Rollouts=72, Iterations=12025.1145.93—
MURPHY - MARSBackbone=Qwen3-1.7B, Rollouts=72, Iterations=12025.1144.73—
BaseBackbone=Qwen3-1.7B, Iterations=12025.1143.47—
MURPHY - MARSBackbone=OLMo-2-1124-7B-Instruct, Rollouts=72, Iterations=32025.1139.6710.07
GRPOBackbone=OLMo-2-1124-7B-Instruct, Rollouts=72, Iterations=32025.1135.86.2
GRPOBackbone=OLMo-2-1124-7B-Instruct, Rollouts=72, Iterations=12025.1132.87—
BaseBackbone=OLMo-2-1124-7B-Instruct, Iterations=32025.1129.6—
MURPHY - MARSBackbone=OLMo-2-1124-7B-Instruct, Rollouts=72, Iterations=12025.1129.33—
BaseBackbone=OLMo-2-1124-7B-Instruct, Iterations=12025.1119.9—