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

Reasoning on GSM→FOL

85.8Accuracy

DIN-ICL

Updated 10d ago

Evaluation Results

Method	Links
DIN-ICL 2026.04		85.8
DIN-ICL 2026.04		85.8
DIN-ICL 2026.04		85
DIN-ICL 2026.04		85
ZERO-SHOT 2026.04		84.5
DIN-ICL 2026.04		84
DIN-ICL 2026.04		84
X-ICL 2026.04		83.6
SET-BSR 2026.04		83.6
X-ICL 2026.04		83.1
SET-BSR 2026.04		83.1
ZERO-SHOT 2026.04		82.2
ZERO-SHOT 2026.04		81.7
X-ICL 2026.04		81.2
SET-BSR 2026.04		81.2
DIN-ICL 2026.04		71.4
DIN-ICL 2026.04		71.4
DIN-ICL 2026.04		70.4
DIN-ICL 2026.04		70.4
ZERO-SHOT 2026.04		70.3
DIN-ICL 2026.04		68.9
DIN-ICL 2026.04		68.9
X-ICL 2026.04		68.4
SET-BSR 2026.04		68.4
ZERO-SHOT 2026.04		67.9
ZERO-SHOT 2026.04		67.4
X-ICL 2026.04		67.4
SET-BSR 2026.04		67.4
X-ICL 2026.04		66
SET-BSR 2026.04		66
DIN-ICL 2026.04		65.5
DIN-ICL 2026.04		65.5
DIN-ICL 2026.04		63.5
DIN-ICL 2026.04		63.5
DIN-ICL 2026.04		63.3
DIN-ICL 2026.04		63.3
X-ICL 2026.04		62.5
SET-BSR 2026.04		62.5
ZERO-SHOT 2026.04		61.8
ZERO-SHOT 2026.04		61
X-ICL 2026.04		59.7
SET-BSR 2026.04		59.7
ZERO-SHOT 2026.04		56.3
X-ICL 2026.04		55.5
SET-BSR 2026.04		55.5