List your company

Research

Benchmarks

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

309,131 benchmarksPage 2064 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Vulnerability Severity PredictionCTIBench-VSPadversarial safety securitycode developer ai17Feb 26, 2026
Root Cause MappingCTIBench RCMnlp17Feb 26, 2026
Multiple Choice Question AnsweringCTIBench MCQAnlp17Feb 26, 2026
Multimodal Autonomous Driving CapabilityDriveBenchmultimodalcomputer vision+117Feb 26, 2026
High-Level ReasoningHLEllm chat instruction17Feb 26, 2026
Agent TaskSudokuagents tool userobotics embodied ai17Feb 26, 2026
Agent TaskFrozenLakeagents tool userobotics embodied ai17Feb 26, 2026
Agent TaskBlocksWorldagents tool userobotics embodied ai17Feb 26, 2026
Agent Behavior AdaptationWebShop (WS) (test)robotics embodied ai17Feb 26, 2026
Agent Behavior AdaptationAlfWorld (AW) (test)robotics embodied ai17Feb 26, 2026
Agent Behavior AdaptationSudoku (Su) (test)robotics embodied ai17Feb 26, 2026
Agent Behavior AdaptationFrozenLake (FL) (test)robotics embodied ai17Feb 26, 2026
Agent Behavior AdaptationBlocksWorld (BW) (test)robotics embodied ai17Feb 26, 2026
Multimodal ReasoningGEO-AT RNAmultimodalnlp17Feb 26, 2026
Multimodal ReasoningGEO-AT DNAmultimodalnlp17Feb 26, 2026
Multimodal ReasoningGEO-AT Proteinmultimodalnlp17Feb 26, 2026
Multimodal ReasoningGEO-AT Moleculemultimodalnlp17Feb 26, 2026
Embodied Task PlanningALFWorld (test)robotics embodied ai17Feb 26, 2026
Opinion Dynamics ModelingCOVID-19 (60 T)tabular time series17Feb 26, 2026
Opinion Dynamics ModelingCOVID-19 (30 T)tabular time series17Feb 26, 2026
Opinion Dynamics ModelingIsrael-Palestine (60 T)tabular time series17Feb 26, 2026
Opinion Dynamics ModelingIsrael-Palestine 30 Ttabular time series17Feb 26, 2026
Opinion Dynamics ModelingU.S. Election 60 Ttabular time series17Feb 26, 2026
Opinion Dynamics ModelingU.S. Election (30 T)tabular time series17Feb 26, 2026
Opinion Dynamics ModelingDelhi Election (60 T)tabular time series17Feb 26, 2026