List your company

Multilingual Reasoning on M-IMO

39.16AccuracyROSA (+LM + M)
0.503210.539120.57530.6109Sep 27, 2025

Evaluation results

MethodLinks
ROSA (+LM + M)Model=Qwen3-8B2025.0939.16
ROSA (+HS + R)Model=Qwen3-8B2025.0937.62
ROSA (+LM + R)Model=Qwen3-8B2025.0933.17
ROSA (+LM + M)Model=Qwen2.5-7B-Instruct2025.0921.21
BaselineModel=Qwen3-8B2025.0920.37
ROSA (+HS + R)Model=Qwen2.5-7B-Instruct2025.0918.36
ROSA (+LM + R)Model=Qwen2.5-7B-Instruct2025.0917.57
BaselineModel=Qwen2.5-7B-Instruct2025.0910.53
ROSA (+LM + M)Model=Qwen3-0.6B2025.096.6
ROSA (+LM + M)Model=DeepSeek-R1-Distill-Llama-8B2025.096.36
ROSA (+LM + R)Model=DeepSeek-R1-Distill-Llama-8B2025.096.32
ROSA (+LM + R)Model=Qwen3-0.6B2025.095.3
ROSA (+HS + R)Model=Qwen3-0.6B2025.095.3
BaselineModel=Qwen3-0.6B2025.095.2
ROSA (+HS + R)Model=DeepSeek-R1-Distill-Llama-8B2025.095.17
ROSA (+LM + M)Model=Qwen2.5-0.5B-Instruct2025.094.71
BaselineModel=DeepSeek-R1-Distill-Llama-8B2025.094.36
ROSA (+HS + R)Model=Qwen2.5-0.5B-Instruct2025.093.2
ROSA (+LM + R)Model=Qwen2.5-0.5B-Instruct2025.092.09
BaselineModel=Qwen2.5-0.5B-Instruct2025.091.99