List your company

Mathematical Reasoning on MultiArith (Accuracy)

99.15AccuracyDMoA
92.629294.322196.01597.7079May 15, 2026

Evaluation results

MethodLinks
DMoABackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0599.15
SafeSieveBackbone=gpt-oss-120b2026.0597.8
G-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0597.6
ARG-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0597.35
GPTSwarmBackbone=gpt-oss-120b2026.0596.28
STEERBackbone=gpt-oss-120b2026.0595.82
LLM-DebateBackbone=gpt-oss-120b2026.0595.45
SpecReasonBackbone=gpt-oss-120b2026.0595.4
AutoGenBackbone=gpt-oss-120b2026.0595.05
Random GraphBackbone=gpt-oss-120b2026.0594.8
Complete GraphBackbone=gpt-oss-120b2026.0594.73
MoABackbone=gpt-oss-120b2026.0594.5
SCBackbone=gpt-oss-120b2026.0594.4
AFlowBackbone=gpt-oss-120b2026.0594.28
CoTBackbone=gpt-oss-120b2026.0593.6
VanillaBackbone=gpt-oss-120b2026.0593.4
StarBackbone=gpt-oss-120b2026.0593.25
TreeBackbone=gpt-oss-120b2026.0592.95
ChainBackbone=gpt-oss-120b2026.0592.88