Share your thoughts, 1 month free Claude Pro on usSee more

Math Reasoning on MultiArith (Accuracy)

98.3Accuracy

POES

Updated 4d ago

Evaluation Results

Method	Links
POES 2026.04		98.3
Anchor 2026.04		98.3
TopLoRA 2026.04		97.67
Random 2026.04		97.5
Prediction 2026.04		97.5
MELoRA 2026.04		97.33
FourierMoE 2026.04		97.33
SESS 2026.04		96.7
POES 2026.04		96.7
Random 2026.04		96.7
Prediction 2026.04		96.7
POES 2026.04		96.7
POES 2026.04		96.7
POES 2026.04		96.7
DoRA 2026.04		96.39
LoRA 2026.04		96.33
HydraLoRA 2026.04		96.22
IPOMP 2026.04		95.8
Anchor 2026.04		95.8
SESS 2026.04		95.8
Prediction 2026.04		95.8
IPOMP 2026.04		95.8
Anchor 2026.04		95
FFT 2026.04		94.43
Prediction 2026.04		94.2
IPOMP 2026.04		94.2
GRASS 2026.04		93.5
Random 2026.04		93.3
Anchor 2026.04		93.3
Prediction 2026.04		93.3
POES 2026.04		93.3
SESS 2026.04		93.3
FourierMoE 2026.04		93.16
DoRA 2026.04		93.16
LoRA 2026.04		92.5
Random 2026.04		92.5
SESS 2026.04		92.5
IPOMP 2026.04		92.5
Random 2026.04		92.5
SESS 2026.04		92.5
IPOMP 2026.04		92.5
DoRA 2026.04		92.17
GRASS 2026.04		92
Random 2026.04		91.7
Prediction 2026.04		91.7
Anchor 2026.04		91.7
LoRA 2026.04		91.5
LoRA 2026.04		91.22
LISA 2026.04		91.17
HydraLoRA 2026.04		91
LoRA 2026.04		90.5
LoRA 2026.04		90.5
LISA 2026.04		90.17
DoRA 2026.04		89.67
IPOMP 2026.04		89.2
MELoRA 2026.04		87.83
FFT 2026.04		86.67
SESS 2026.04		85
Anchor 2026.04		78.3
GRASS 2026.04		68
DoRA 2026.04		67.83
LoRA 2026.04		65.5
LISA 2026.04		65
FFT 2026.04		64.17
LoRA 2026.04		61.17