List your company

General Language Understanding on P3 v1 (unseen)

80.83RTE AccuracyT0-11B
51.91859.42466.9374.436May 23, 2023

Evaluation results

MethodLinks
T0-11BEvaluation Protocol=Direct2023.0580.8370.1243.5638.6841.2690.0233.5892.459.9461.4556.5860.76
T0-3B + COT FTEvaluation Protocol=Direct2023.0580.796539.4935.1338.5888.2741.0492.1356.465.9653.659.67
T5-3B + COT FTEvaluation Protocol=CoT2023.0580.6169.1740.2436.6740.1390.141.089356.4755.156.7359.94
T0-3B + COT FTEvaluation Protocol=CoT2023.0580.2572.6241.7137.2241.8990.8839.594.4757.4750.5854.2760.08
KiC-770MEvaluation Protocol=Direct2023.057467.936.33537.685.329.694.455.365.452.457.56
FLIPPED-3BEvaluation Protocol=Direct2023.0571.0557.7439.9937.0537.7389.8841.6495.8858.5658.3750.4258.03
T5-3B + COT FTEvaluation Protocol=Direct2023.0569.9658.6937.583637.4484.5940.9290.4755.464.3351.5356.99
RoE-3BEvaluation Protocol=Direct2023.0564.0143.5735.4934.6431.2279.2534.686.3361.662.2152.9753.48
GPT-3 (175B)Evaluation Protocol=Direct2023.0563.546.434.635.434.59178.983.270.265.445.9259
T0-3BEvaluation Protocol=Direct2023.0560.6148.8135.133.2733.5275.1327.1884.9150.916551.2751.43
T5-3BEvaluation Protocol=Direct2023.0553.0334.3432.8933.7633.8254.882748.1650.6454.0950.342.99