List your company

Research

Benchmarks

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

309,131 benchmarksPage 1577 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Explainable AI EvaluationImageNet Non-Balanced Classcomputer vision20Apr 21, 2026
Explainable AI EvaluationImageNet Balanced Classcomputer vision20Apr 21, 2026
Explainable AI EvaluationImageNet-1K Non-Balanced Class 1.0 (test)computer vision20Apr 21, 2026
Explainable AI EvaluationImageNet-1K Balanced Class 1.0 (test)computer vision20Apr 21, 2026
Step-level reasoning evaluationPDDL (test)agents tool usellm chat instruction20Apr 21, 2026
Style TransferCSG-Benchimage generation editingnlp20Apr 21, 2026
reference-guided style transferOmniConsistency-Benchimage generation editingcomputer vision20Apr 21, 2026
Selective predictionClassical Minds metacognitive battery (test)nlp20Apr 21, 2026
End-to-end policy optimizationSequential cooperative bandit testbed (test)robotics embodied ai20Apr 21, 2026
RecommendationFoodtabular time series20Apr 30, 2026
Base-to-New GeneralizationMedMNIST+ Base-to-New v2computer vision20Apr 21, 2026
Multi-hop Question AnsweringBamboogle Wiki-18nlpretrieval search rag20Apr 21, 2026
Multi-hop Question AnsweringMuSiQue Wiki-18nlpretrieval search rag20Apr 21, 2026
Multi-hop Question Answering2Wiki 18nlpretrieval search rag20Apr 21, 2026
Multi-hop Question AnsweringHotpotQA Wiki-18nlpretrieval search rag20Apr 21, 2026
Tool UsageAggregate BFCL and Meta-Toolagents tool use20Apr 21, 2026
Tool UsageMeta-Tool Multipleagents tool use20Apr 21, 2026
Tool UsageMeta-Tool Singleagents tool use20Apr 21, 2026
Tool UsageBFCL Multi-Parallel v2agents tool use20Apr 21, 2026
Tool UsageBFCL Parallel v2agents tool use20Apr 21, 2026
Tool UsageBFCL Multi-Parallel v1agents tool use20Apr 21, 2026
Tool UsageBFCL Parallel v1agents tool use20Apr 21, 2026
Multi-Hop Question AnsweringBambooglenlpretrieval search rag20Apr 21, 2026
Multi-Hop Question Answering2Wikinlpretrieval search rag20Apr 21, 2026
Multi-Hop Question AnsweringHotpotQAnlpretrieval search rag20Apr 21, 2026