List your company

Research

Benchmarks

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

309,131 benchmarksPage 629 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Question AnsweringAmbigQAnlp36May 26, 2026
Out-of-Distribution Action DetectionTHUMOS14computer vision36May 26, 2026
Policy LearningHIV datasetrobotics embodied ai36May 26, 2026
Uncertainty EstimationReal-Noisenlp36May 26, 2026
Code GenerationMBPPcode developer ai36Jul 1, 2026
Long-form generation hallucination evaluationCHAIRllm chat instructionnlp36May 26, 2026
Network AlignmentACM-DBLP-Agraph36May 26, 2026
Network AlignmentACM-DBLP-Pgraph36May 26, 2026
Network AlignmentPhone-Emailgraph36May 26, 2026
Secure Code GenerationLLMSecEval 150 taskscode developer aiadversarial safety security36May 26, 2026
Fault DetectionCifar-100tabular time series36May 26, 2026
Fault DetectionCifar-10tabular time series36May 26, 2026
Audio Understanding RobustnessMMAU Sound (SNR=-10dB)speech audioadversarial safety security36May 26, 2026
Action RecognitionHMDB-51computer vision36May 25, 2026
Reasoning15 reasoning benchmarks weighted mean (test)llm chat instructionnlp36May 25, 2026
Mathematical ReasoningHMMT25llm chat instructionnlp36Jun 9, 2026
Motion-compensated 3D Brain MRI ReconstructionFastMRI multicoil T1-weighted (test)3d vision geometrybio medical36May 22, 2026
Clinical diagnosisS3 1.0 (test)bio medical36May 22, 2026
Class Prior EstimationBanknotetabular time series36May 22, 2026
Class Prior EstimationVehicletabular time series36May 22, 2026
Class Prior EstimationYeasttabular time series36May 22, 2026
Class Prior EstimationWaveformtabular time series36May 22, 2026
Class Prior EstimationSegmenttabular time series36May 22, 2026
Class Prior EstimationSpambasetabular time series36May 22, 2026
Class Prior EstimationDiabetestabular time series36May 22, 2026