List your company

Research

Benchmarks

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

309,131 benchmarksPage 2130 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Route TracingMapTracecomputer vision16Jun 12, 2026
Visual ProbingVisualProbe Hardcomputer visionmultimodal16Jun 12, 2026
Visual ProbingVisualProbe Mediumcomputer visionmultimodal16Jun 12, 2026
Visual ProbingVisualProbe Easycomputer visionmultimodal16Jun 12, 2026
Spatial ReasoningReasonMapnlp16Jun 12, 2026
Spatial ReasoningReasonMap Plusnlp16Jun 12, 2026
MulticalibrationCOMPAStabular time series16Jun 12, 2026
Certified Robustness VerificationMNIST first 50 samples (test)computer visionadversarial safety security16Jun 12, 2026
Tool Attack DefenseMulti-Agent System (MAS) Topologies Average of Chain, Tree, Star, Randomagents tool useadversarial safety security16Jun 12, 2026
Prompt Injection DefenseMulti-Agent System (MAS) Topologies Average of Chain, Tree, Star, Randomadversarial safety security16Jun 12, 2026
Robot ManipulationManiSkill Table-Top 2 Finger Gripper (Overall)robotics embodied ai16Jun 11, 2026
Robot ManipulationManiSkill RollBall v1robotics embodied ai16Jun 11, 2026
Robot ManipulationManiSkill PokeCube v1robotics embodied ai16Jun 11, 2026
Robot ManipulationManiSkill PushCube v1robotics embodied ai16Jun 11, 2026
Short-video Question AnsweringShort-video QA Suite NextQA, PerceptionTest, MVBench, Tomato, MotionBench, TempCompassmultimodalcomputer vision16Jun 11, 2026
SCPI extractionSCPI extraction corpusnlp16Jun 11, 2026
LocomotionHalfCheetahrobotics embodied ai16Jun 11, 2026
Robotic ManipulationMeta-World modified (test)robotics embodied ai16Jun 11, 2026
Theory of Mind reasoningHi-ToMnlp16Jun 11, 2026
Theory of Mind ReasoningFanToMnlp16Jun 11, 2026
Agentic PerformanceOSWorld Verifiedagents tool use16Jun 11, 2026
Concept Faithfulness EvaluationAGNEWSnlp16Jun 11, 2026
Concept Faithfulness EvaluationJigsawnlp16Jun 11, 2026
Concept Faithfulness EvaluationERASER Movienlp16Jun 11, 2026
Aggregated Multi-task EvaluationAveragellm chat instructionnlp+116Jun 11, 2026