List your company

Research

Benchmarks

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

309,131 benchmarksPage 2005 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Temporal language groundingQVHighlights (test)computer visionnlp17May 13, 2026
RegressionDiabetes datasettabular time series17May 19, 2026
Zero-shot Evaluation0-shotnlpllm chat instruction17May 13, 2026
Table Question AnsweringTAT-QAnlpretrieval search rag17May 13, 2026
Language ModelingWikiText-103nlp17Jun 24, 2026
ClassificationScanObjectNN v2computer visionnlp+317May 12, 2026
Web interactionMind2Web (cross-website)agents tool use17Jun 24, 2026
Closed-loop End-to-End Autonomous DrivingBench2Drive (base set)robotics embodied aicomputer vision17May 12, 2026
Streaming Video UnderstandingOVO-Bench RealStreamEval protocolcomputer vision17May 12, 2026
Image RetrievalStanford Cars 196retrieval search ragcomputer vision17May 12, 2026
Pairwise relationship classificationStreet-view fine-tuning dataset (test)computer vision17May 12, 2026
Constraint SatisfactionGears Worldmiscellaneous17May 12, 2026
Language Agent TaskTextCraftagents tool usellm chat instruction17Jun 25, 2026
Multimodal Role-playingMMRole (out-of-domain)multimodalllm chat instruction17May 12, 2026
Multi-modal Role-playingMMRole in-domainmultimodalllm chat instruction17May 12, 2026
Causal DiscoveryPROCAUEVAL Deprivation 1.0tabular time series17May 12, 2026
Causal DiscoveryPROCAUEVAL Incongruence 1.0tabular time series17May 12, 2026
Causal DiscoveryPROCAUEVAL Plausibility 1.0tabular time series17May 12, 2026
Causal DiscoveryPROCAUEVAL Veridicality 1.0tabular time series17May 12, 2026
PlanningTwo-Roomrobotics embodied ai17Jun 26, 2026
Machine Translation Meta-evaluationWMT EN-UK 2025nlp17May 12, 2026
Machine Translation Meta-evaluationWMT EN-JA 2025nlp17May 12, 2026
Machine Translation Meta-evaluationWMT EN-ZH 2025nlp17May 12, 2026
Machine Translation Meta-evaluationWMT EN-CS 2025nlp17May 12, 2026
Multi-Doc Question AnsweringLongBench-E Multi-Doc QAretrieval search ragnlp17May 12, 2026