List your company

Tool Using on Live P-Mul

70.83AccuracyToolRL
-2.833216.290935.41554.5391Jun 1, 2026

Evaluation results

MethodLinks
ToolRLModel Category=Base and Expert Models2026.0670.83
RESMERGEModel Category=Merged Models2026.0670.83
Qwen2.5-7B-InstructModel Category=Base and Expert Models2026.0666.67
MemoryAgentModel Category=Base and Expert Models2026.0666.67
TAModel Category=Merged Models2026.0666.67
TIESModel Category=Merged Models2026.0666.67
DARE + TIESModel Category=Merged Models2026.0666.67
TSV-MergeModel Category=Merged Models2026.0666.67
ISO-CModel Category=Merged Models2026.0666.67
ISO-CTSModel Category=Merged Models2026.0666.67
RAMModel Category=Merged Models2026.0666.67
General-ReasonerGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0658.33
AMPOModel Category=Base and Expert Models2026.0650
TAGroup=Qwen3-4B-Base, Category=Merged Models2026.0637.5
RESMERGEGroup=Qwen3-4B-Base, Category=Merged Models2026.0637.5
TSV-MergeGroup=Qwen3-4B-Base, Category=Merged Models2026.0633.33
GRPOGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0629.17
Qwen3-4BGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0625
RAMGroup=Qwen3-4B-Base, Category=Merged Models2026.0620.83
TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.0616.67
SpiralGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.0612.5
DARE + TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.060