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

Accuracy on OpenBookQA

96.07Accuracy

PromptWizard

Updated 1mo ago

Evaluation Results

Method	Links
PromptWizard 2026.05		96.07
Zero-Shot CoT 2026.05		95.8
Spurious 2026.05		95.67
Least-to-Most 2026.05		95.6
Spurious Universal 2026.05		95.49
Re-Reading 2026.05		95.2
Plan-and-Solve 2026.05		95
Analogical 2026.05		94.4
Step-Back 2026.05		93.8
Self-Ask 2026.05		91.8
Zero-Shot CoT 2026.05		86.2
PromptWizard 2026.05		86.07
SafeInstr 2026.05		84.15
Re-Reading 2026.05		84
SFT 2026.05		83.7
SafeGrad 2026.05		83.3
PTST 2026.05		83.25
SPARD 2026.05		83.25
TSDS 2026.04		82
Step-Back 2026.05		81.8
Spurious 2026.05		81.4
EVOSELECT 2026.04		81
EVOSELECT 2026.04		80.8
EVOSELECT 2026.04		80.8
Random 2026.04		80.6
EVOSELECT 2026.04		80.6
TSDS 2026.04		80.6
All 2026.04		80.4
Random 2026.04		80.2
Attribution 2026.04		80.2
Base 2026.04		80
Attr-Div 2026.04		79.8
Attr-Div 2026.04		79.8
Random 2026.04		79.8
Diversity 2026.04		79.8
Attribution 2026.04		79.6
Attr-Div 2026.04		79.4
Attribution 2026.04		79.2
TSDS 2026.04		79.2
Analogical 2026.05		79
Plan-and-Solve 2026.05		79
Lisa 2026.05		78.9
TSDS 2026.04		78.8
Attr-Div 2026.04		78.8
Diversity 2026.04		78.6
Diversity 2026.04		78.6
Attribution 2026.04		78
Random 2026.04		77.8
All 2026.04		77.6
Qwen-2.5-7B-Instruct 2026.05		77.6
Diversity 2026.04		76.6
Unpruned 2026.04		76
Least-to-Most 2026.05		74.4
Self-Ask 2026.05		73
Spurious Universal 2026.05		72.4
Analogical 2026.05		67.4
Re-Reading 2026.05		67
Zero-Shot CoT 2026.05		66.4
Step-Back 2026.05		65.4
MTO-AP 2026.06		65.2
PromptWizard 2026.05		65
Roberta-large 2026.06		64.8
MTO-MP 2026.06		64.8
MTO-D+MCP 2026.06		64
MTO-MAP 2026.06		62.8
Plan-and-Solve 2026.05		62.6
T5-large 2026.06		61.8
Spurious Universal 2026.05		61.47
Least-to-Most 2026.05		59.4
Spurious 2026.05		59.13
LC-QAT 1.7B 2026.06		55.2
r-c3LA 2026.06		53.69
PromptWizard 2026.05		53.4
Zero-Shot CoT 2026.05		53
LoRA 2026.06		52.41
Spurious 2026.05		51.6
Step-Back 2026.05		50.8
Analogical 2026.05		50.8
Plan-and-Solve 2026.05		50.2
Nautile-370M 2026.04		49.3
Tokenizer-based 2026.05		49.2
Spurious Universal 2026.05		48.93
SpaceByte + SP 2026.05		48
Re-Reading 2026.05		48
Least-to-Most 2026.05		46.8
Entropy-based 2026.05		46.4
Fixed (p = 4) + SP 2026.05		46
H-Net + SP 2026.05		45.8
H-Net 2026.05		45.6
Entropy-based + SP 2026.05		45.4
BF16 2026.05		45.2
Byte-level 2026.05		45.2
Fixed (p = 4) 2026.05		44.8
SpaceByte 2026.05		44.8
Fixed (p = 8) + SP 2026.05		44.4
BF16 2026.05		44.2
MR-GPTQ 2026.04		43.4
Fixed (p = 16) + SP 2026.05		43.4
MR-GPTQ 2026.04		43
FP16 2026.04		43

Showing 100 of 319 rows