Commonsense Reasoning on COPA (test)

98.67Accuracy

OPRO

Updated 2d ago

Evaluation Results

Method	Links
OPRO 2025.04		98.67
CAPO 2025.04		98.47
CAPO 2025.04		98.27
Initial 2025.04		98.27
PromptWizard 2025.04		98.13
OPRO 2025.04		98.07
EvoPromptGA 2025.04		97.87
Initial 2025.04		97.65
EvoPromptGA 2025.04		97.6
OPRO 2025.04		96.33
EvoPromptGA 2025.04		96.13
CAPO 2025.04		95.13
Initial 2025.04		94.56
Coherence Boosting (GPT-3 175B) 2021.10		94
GPT-3 175B 2021.10		93
AUSteer-FFN 2026.02		91.2
AUSteer-Head 2026.02		91
AUSteer-Head 2026.02		90.2
FedTT 2024.10		90
AUSteer-FFN 2026.02		89.8
LoRA 2024.10		89
FedTT 2024.10		89
Vanilla 2026.02		89
FedTT+ 2024.10		88
GPT-3 175B 2021.10		87
LoRA 2024.10		87
AUSteer-Head 2026.02		86
AUSteer-FFN 2026.02		86
Vanilla 2026.02		86
MeZO 2026.05		86
ZoVH 2026.05		85.67
Vanilla 2026.02		83.8
ZoVH 2026.05		83.33
HiZOO 2026.05		80.67
KELM 2021.09		78
Coherence Boosting (GPT-2 XL) 2021.10		77
ZoVH 2026.05		76.67
HiZOO 2026.05		76
MeZO 2026.05		75.33
ZoVH 2026.05		73.67
GPT-2 XL (1.6B) 2021.10		73
Sasaki et al. 2018.10		71.2
BERT-large 2021.09		70.6
Luo et al. 2018.10		70.2
GPT-2 XL (1.6B) 2021.10		70
AGQ 2018.10		66.2
Gordon et al. 2018.10		65.4
AGQS 2018.10		65.1
Coherence Boosting (GPT-2 Small) 2021.10		64
Goodwin et al. 2018.10		63.4
GPT-2 Small (125M) 2021.10		62
PromptWizard 2025.04		57.47
GPT-2 Small (125M) 2021.10		56
PromptWizard 2025.04		50.33