List your company

Research

Benchmarks

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

309,131 benchmarksPage 836 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ReconstructionMRIcomputer vision30May 26, 2026
Uncertainty EstimationGaussian noise datasetnlp30May 26, 2026
Uncertainty EstimationPoisson noise datasetnlp30May 26, 2026
Temporal Link PredictionCollegeMsg (inductive)graph30May 26, 2026
Temporal Link PredictionUCI (inductive)graph30May 26, 2026
Multi-turn MathGSM8K multi-turnllm chat instructionnlp30May 26, 2026
Multi-turn math reasoningSHARDEDllm chat instructionnlp30May 26, 2026
CNOT circuit synthesis4 x 4 MDS matrices over GL(8, F2)miscellaneous30May 26, 2026
Harmful Meme DetectionEx-ToxiCN-MM (test)computer visionnlp30May 26, 2026
MDD DiagnosisREST-meta-MDD site 20 (test)bio medicaltabular time series30May 26, 2026
Vulnerability DetectionZKAP Datasetadversarial safety securitycode developer ai30May 26, 2026
Vulnerability DetectionReal-world ZK Circuits Alladversarial safety securitycode developer ai30May 26, 2026
Safety classification disagreementWildChat Contentadversarial safety securityllm chat instruction30May 26, 2026
Safety classification disagreementWildChat Intentadversarial safety securityllm chat instruction30May 26, 2026
Multilingual Mathematical ReasoningPolyMath (test)nlpllm chat instruction30May 22, 2026
10-step incompressible flow rolloutNS-SL extreme viscosity (x) (test)miscellaneous30May 22, 2026
10-step incompressible flow rolloutNS-SL moderate viscosity (m) (test)miscellaneous30May 22, 2026
Machine TranslationWildMTBenchnlp30May 22, 2026
Machine TranslationDomainMTBenchnlp30May 22, 2026
Machine TranslationMandarin ⇔ Minority (General)nlp30May 22, 2026
Machine TranslationFLORES-200 XX ⇔ XXnlp30May 22, 2026
Machine TranslationFLORES-200 ZH ⇔ XXnlp30May 22, 2026
Question AnsweringNQ (test)nlp30May 22, 2026
RDP AuditingCIFAR-10adversarial safety security30May 22, 2026
RDP AuditingMNISTadversarial safety security30May 22, 2026