List your company

Research

Benchmarks

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

309,131 benchmarksPage 1447 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Information RetrievalFiQAretrieval search rag21May 11, 2026
Information RetrievalSciFactretrieval search rag21May 11, 2026
Information RetrievalHQAretrieval search rag21May 11, 2026
Information RetrievalNQretrieval search rag21May 11, 2026
RetrievalMS MARCOretrieval search rag21May 11, 2026
Multi-hop Question AnsweringBambooglenlpretrieval search rag21May 11, 2026
Mathematical ReasoningHMMT 2025 (Feb)llm chat instructionnlp21May 8, 2026
Link PredictionHetionetgraph21Jun 2, 2026
Pest ClassificationQFSD (test)computer vision21May 8, 2026
Pest ClassificationAgriInsect (test)computer vision21May 8, 2026
Mathematical ReasoningiGSMllm chat instructionnlp21May 8, 2026
Medical Image ClassificationPneumoniaMNISTbio medicalcomputer vision21May 27, 2026
Aerodynamic Field PredictionSuperWing (test)tabular time series21May 8, 2026
General ReasoningAIME 25llm chat instructionnlp21May 20, 2026
Robotic ManipulationCan-Imagerobotics embodied ai21May 7, 2026
Text+Image EditingCoSTA Text+Image Tasks 1.0 (test)image generation editingmultimodal21May 7, 2026
Solving Quadratic Nonlinear Schrödinger EquationQuadratic Nonlinear Schrödinger Equation (T=1.0, N=1024, γ=0.5)miscellaneous21May 7, 2026
Safety EvaluationHEx-PHI Alpaca risk-ranked subsetsadversarial safety security21May 7, 2026
Safety EvaluationHEx-PHI Dolly risk-rankedadversarial safety security21May 7, 2026
Safety EvaluationCategoricalHarmfulQA Dolly fine-tuning (test)adversarial safety security21May 7, 2026
ClassificationFPHA standard predefinedcomputer visionnlp+321May 7, 2026
Action RecognitionHDM05 (5-fold stratified cross-validation)computer vision21May 7, 2026
Federated Backdoor DefenseEMNISTadversarial safety security21May 7, 2026
Federated Backdoor DefenseCIFAR100adversarial safety security21May 7, 2026
Alzheimer’s disease diagnosisDARWINbio medicaltabular time series21May 7, 2026