List your company

Mathematical Reasoning on MATH Overall

68.5SRLC-ERD (Dual-72B)
45.30851.32957.3563.371May 19, 2026

Evaluation results

MethodLinks
LC-ERD (Dual-72B)#Params=144B, VRAM (Avg.)=~112GB, Time (Rel.)=~2.1x, Multi-agent or MARL framework=true2026.0568.5
LC-ERD (72B)#Params=72B, VRAM (Avg.)=~56GB, Time (Rel.)=~1.8x, Multi-agent or MARL framework=true2026.0565.2
InfiGUI-R1#Params=72B, VRAM (Avg.)=~63GB, Time (Rel.)=~1.3x, Multi-agent or MARL framework=true2026.0562.8
PRM#Params=72B+, VRAM (Avg.)=~64GB, Time (Rel.)=~1.6x, Multi-agent or MARL framework=true2026.0558.4
MaAS#Params=72B+, VRAM (Avg.)=~60GB, Time (Rel.)=~2.1x, Multi-agent or MARL framework=true2026.0557.8
Gen-Verifier#Params=72B, VRAM (Avg.)=~68GB, Time (Rel.)=~2.1x2026.0556.8
AFlow#Params=72B+, VRAM (Avg.)=~64GB, Time (Rel.)=~3.2x, Multi-agent or MARL framework=true2026.0555.4
EndoRM#Params=72B, VRAM (Avg.)=~54GB, Time (Rel.)=~1.4x2026.0553.9
LPO#Params=72B, VRAM (Avg.)=~52GB, Time (Rel.)=~1.5x2026.0553.4
STaR#Params=72B, VRAM (Avg.)=~58GB, Time (Rel.)=~2.5x, Multi-agent or MARL framework=true2026.0552.1
Iterative-DPO#Params=72B, VRAM (Avg.)=~56GB, Time (Rel.)=~2.1x2026.0551.3
SimPO#Params=72B, VRAM (Avg.)=~52GB, Time (Rel.)=~1.1x2026.0549.8
DPO#Params=72B, VRAM (Avg.)=~52GB, Time (Rel.)=~1.8x2026.0548.5
Qwen2.5-72B (Base)#Params=72B, VRAM (Avg.)=~52GB, Time (Rel.)=1.0x (SFT)2026.0546.2