List your company

Research

Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 benchmarksPage 636 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Relative Robustness AnalysisCombined Past Tense, OR-Bench, MMLUllm chat instruction36Apr 15, 2026
Global Counterfactual ExplanationsHELOCtabular time series36Apr 15, 2026
Global Counterfactual ExplanationsGerman Credittabular time series36Apr 15, 2026
Global Counterfactual ExplanationsDefault Credittabular time series36Apr 15, 2026
Global Counterfactual ExplanationsCOMPAStabular time series36Apr 15, 2026
Image ClassificationFood-101 (test)computer vision36Jun 30, 2026
Speech RecognitionSwitchboard eval00speech audio36Apr 14, 2026
Face VerificationRFWcomputer vision36Jun 4, 2026
Medical Diagnostic ReasoningMedCaseReasoning official 897-case (test)bio medicalllm chat instruction36Apr 14, 2026
Creative WritingCreative Writingllm chat instruction36Apr 14, 2026
Question AnsweringSQuAD KRE-curated versionnlp36Apr 14, 2026
Open-ended Question AnsweringConFiQA (test)retrieval search ragnlp36Apr 14, 2026
Multi-step Reasoning Question AnsweringConFiQA MR (test)llm chat instructionnlp36Apr 14, 2026
PoisoningCIFAR100adversarial safety security36Apr 14, 2026
PoisoningCIFAR10adversarial safety security36Apr 14, 2026
Artistic Style ErasureSD Other Class artistic styles 1.4 (test)image generation editing36Apr 14, 2026
Artistic Style ErasureSD Target Class artistic styles 1.4 (test)image generation editing36Apr 14, 2026
Linear RegressionEqui-correlation Sigma_a r=0.3tabular time series36Apr 14, 2026
Linear RegressionEqui-correlation Sigma_a r=0.1tabular time series36Apr 14, 2026
Linear regressionLinear regression with Toeplitz Sigma_a r=0.6tabular time series36Apr 14, 2026
Linear regressionLinear regression with Toeplitz Sigma_a r=0.4tabular time series36Apr 14, 2026
Partial Multi-Label Learningreferencecomputer vision36Apr 13, 2026
Partial Multi-Label Learningartscomputer vision36Apr 13, 2026
Partial Multi-Label Learningreferencecomputer vision36Apr 13, 2026
Partial Multi-Label Learningartscomputer vision36Apr 13, 2026