List your company

Mathematical Reasoning on GSM Hard (Accuracy, Latency, SLO)

62AccuracyINFRAMIND
48.58452.06755.5559.033Jun 9, 2026

Evaluation results

MethodLinks
INFRAMINDLoad level=10 req/min2026.066237100
INFRAMINDLoad level=50 req/min2026.06607698.8
INFRAMINDLoad level=100 req/min2026.0657.28198.4
GPTSwarmLoad level=50 req/min2026.065770714.8
MASRouterLoad level=100 req/min2026.0656.465220.6
MASRouterLoad level=50 req/min2026.065552127.4
MASRouterLoad level=10 req/min2026.0654.638100
GPTSwarmLoad level=10 req/min2026.065452100
GPTSwarmLoad level=100 req/min2026.06548069
MoALoad level=100 req/min2026.065052511.2
MoALoad level=10 req/min2026.0649.338100
MoALoad level=50 req/min2026.0649.147416.8