List your company

Research

Benchmarks

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

309,131 benchmarksPage 755 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Expert PlacementCanonical multi-task workloadmiscellaneous32Jun 2, 2026
Video Question AnsweringVideoMMEmultimodalcomputer vision32Jul 7, 2026
Speculative DecodingAvg.llm chat instruction32Jun 26, 2026
Pointwise evaluationBIGGENllm chat instruction32Jun 1, 2026
Text ClassificationGLUEnlp32Jun 1, 2026
Camera Pose EstimationScanNet++3d vision geometrycomputer vision32Jul 7, 2026
Depth CompletionETH3D (test)3d vision geometrycomputer vision32May 29, 2026
EEG Super-ResolutionLocalize-MI 256 ch.bio medicaltabular time series32May 29, 2026
ReasoningMath Visionllm chat instructionnlp32May 28, 2026
Radio Environmental MappingRadioMapSeermiscellaneous32May 28, 2026
Video Sentence GroundingActivityNet Captionscomputer visionnlp32May 28, 2026
Graph Anomaly DetectionT-Socialgraph32May 28, 2026
Multimodal Dental Question AnsweringMMOral-Unimultimodalbio medical+232May 28, 2026
Higher-frequency wave-field predictionMaxwell (test)miscellaneous32May 27, 2026
Higher-frequency wave-field predictionHelmholtz (test)miscellaneous32May 27, 2026
Higher-frequency wave-field predictionSimpleWave (test)miscellaneous32May 27, 2026
Uncertainty EstimationSecret-word taboo dataset (random-split)nlp32May 26, 2026
Cross-lingual RetrievalWebFAQretrieval search ragnlp32May 26, 2026
Logical ReasoningK&K tasksnlp32May 26, 2026
Mathematical ReasoningAMC 2023llm chat instructionnlp32Jun 30, 2026
Visual Prompt Injection DefenseImgHijack Specific String (test)adversarial safety securitymultimodal32May 26, 2026
Offline Reinforcement LearningMuJoCo Hopper Friction shiftrobotics embodied ai32May 26, 2026
Offline Reinforcement LearningMuJoCo Walker2d Friction shiftrobotics embodied ai32May 26, 2026
Offline Reinforcement LearningMuJoCo Walker2d Gravity shiftrobotics embodied ai32May 26, 2026
Offline Reinforcement LearningMuJoCo Ant Friction shiftrobotics embodied ai32May 26, 2026