List your company

Instruction Following on Math-IF

61.97IF-RT ScoreStaged Decoding
26.755635.897845.0454.1822Feb 27, 2026

Evaluation results

MethodLinks
Staged DecodingFamily=Qwen 3, Size (B)=82026.0261.9776.4169.19
IF-RT chkpt.Family=Qwen 3, Size (B)=82026.0261.823749.41
IF-RT chkpt.Family=Qwen 3, Size (B)=142026.0253.1125.8539.48
Staged DecodingFamily=Qwen 3, Size (B)=142026.0253.1182.6167.86
IF-RT chkpt.Family=Qwen 3, Size (B)=42026.0251.6126.138.86
Staged DecodingFamily=Qwen 3, Size (B)=42026.0251.6172.4662.04
Staged DecodingFamily=Phi 4, Size (B)=142026.0245.8666.2156.04
IF-RT chkpt.Family=Phi 4, Size (B)=142026.0245.7132.7339.22
IF-RT chkpt.Family=Phi 4, Size (B)=3.82026.0245.3827.3836.38
Staged DecodingFamily=Phi 4, Size (B)=3.82026.0245.3845.7345.56
IF-RT chkpt.Family=Qwen 3, Size (B)=1.72026.0241.4421.6931.56
Staged DecodingFamily=Qwen 3, Size (B)=1.72026.0241.3751.2646.31
BaselineFamily=Qwen 3, Size (B)=82026.0236.759.8948.29
Avg. IF chkpt.Family=Qwen 3, Size (B)=142026.0236.471.7154.05
BaselineFamily=Qwen 3, Size (B)=142026.0236.1773.0454.61
Avg. IF chkpt.Family=Phi 4, Size (B)=142026.0235.1279.7757.44
IF-FA chkpt.Family=Phi 4, Size (B)=142026.0234.8677.4856.17
IF-FA chkpt.Family=Qwen 3, Size (B)=82026.0234.7461.2247.98
Avg. IF chkpt.*Family=Qwen 3, Size (B)=82026.0234.7461.2247.98
BaselineFamily=Phi 4, Size (B)=142026.0234.5479.1456.84
IF-FA chkpt.Family=Qwen 3, Size (B)=142026.0234.4672.8253.64
BaselineFamily=Qwen 3, Size (B)=1.72026.0234.2145.2839.75
IF-FA chkpt.Family=Qwen 3, Size (B)=1.72026.0233.7339.7336.73
Avg. IF chkpt.*Family=Qwen 3, Size (B)=1.72026.0233.7339.7336.73
BaselineFamily=Qwen 3, Size (B)=42026.0233.4163.6348.52
BaselineFamily=Phi 4, Size (B)=3.82026.0230.2538.8134.53
IF-FA chkpt.Family=Qwen 3, Size (B)=42026.0228.8762.9845.92
Avg. IF chkpt.*Family=Qwen 3, Size (B)=42026.0228.8762.9845.92
IF-FA chkpt.Family=Phi 4, Size (B)=3.82026.0228.1136.6532.38
Avg. IF chkpt.*Family=Phi 4, Size (B)=3.82026.0228.1136.6532.38