SOTA Prompt Optimization benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
XSum	EGE	Hypervolume (HV)0.1626	72	19d ago
Prompt Optimization Benchmark	LinGO	Accuracy69	24	3mo ago
Logical Reasoning, Mathematical Calculation, and Knowledge Intensive tasks Average	MemAPO	Average Performance (%)70.7	20	2mo ago
VisEval	PromptAgent	Accuracy (Easy)0.77	10	3mo ago
DABench	PromptBreeder	Acc (Easy)80	10	3mo ago
HotpotQA, IFBench, HoVer, PUPA, AIME, and LiveBench-Math 2018-2025 (test)	GEPA	HotpotQA Score69	8	3mo ago
DSG-1K	CRAFT	DSGScore0.91	7	3mo ago
P2-hard	Maestro	DSGScore92	7	3mo ago
10-task prompt optimization suite GSM8K MMLU BBH	ReElicit	Average Win/Tie Rate81	5	14d ago
product-gen (test)	Bayesian	Accuracy92.2	5	1mo ago
trip-advisory (test)	COPRO-R	Accuracy81.1	5	1mo ago
code-explain (test)	COPRO-R	Accuracy84.2	5	1mo ago
42 LLM benchmarks Aggregate (overall)	System+Task Optimized	Average Score67.14	5	1mo ago
GEPA Evaluation Suite Aggregate	LEVI	Aggregate Score62.02	4	21d ago
PUPA	GEPA	Score91.85	4	21d ago
Hover	GEPA	Score52.33	4	21d ago
IFBench	LEVI	Score46.33	4	21d ago
HotpotQA	LEVI	Score63	4	21d ago
website-gen (test)	COPRO-R	Accuracy53.5	4	1mo ago
Flickr	EDITOR	Mean CLIP Score77.62	4	2mo ago
Dataset with human annotations (test)	LinGO (RAG)	Accuracy69	4	3mo ago

Showing 21 of 21 rows