List your company

Multilingual Reasoning and General Knowledge on Overall (18 languages)

61.91AccuracySP3F-7B
12.905225.627638.3551.0724Jan 26, 2026

Evaluation results

MethodLinks
SP3F-7BTraining Stage=Full Pipeline2026.0161.9195.35
Qwen2.5-7B + RLVRTraining Stage=SFT + RLVR2026.0157.7996.09
Qwen2.5-7B-Instruct + Translate TestTraining Stage=Instruct, Evaluation Protocol=Translate Test2026.0157.0185.98
Qwen2.5-7B-InstructTraining Stage=Instruct2026.0155.8789.21
Qwen2.5-7B + SFTTraining Stage=SFT2026.0121.782.11
Qwen2.5-7BTraining Stage=Base2026.0114.7978.78