List your company

Multilingual Evaluation on GSM8K, IFEval, MMLU Aggregate

40.9Average ScoreRA-MoE
19.5825.11530.6536.185May 27, 2026

Evaluation results

MethodLinks
RA-MoEModel=Qwen1.52026.0540.9
RISEModel=Qwen1.52026.0539.9
SFTModel=Qwen1.52026.0539.3
RA-MoEModel=DSV22026.0539.1
RISEModel=DSV22026.0538.3
SFTModel=DSV22026.0538.1
RSModel=DSV22026.0534.9
0-shotModel=DSV22026.0534.6
RSModel=Qwen1.52026.0529.8
0-shotModel=Qwen1.52026.0529.5
RA-MoEModel=OLMoE2026.0524.2
RISEModel=OLMoE2026.0523.5
SFTModel=OLMoE2026.0523.3
RSModel=OLMoE2026.0520.7
0-shotModel=OLMoE2026.0520.4