List your company

Research

Benchmarks

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

309,131 benchmarksPage 2006 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Single-Doc Question AnsweringLongBench-E Single-Doc QAnlpretrieval search rag17May 12, 2026
Radar-Camera Depth EstimationnuScenes 80m range v1.0-trainval (val)3d vision geometrycomputer vision17May 12, 2026
Classificationblood-transfusioncomputer visionnlp+317May 12, 2026
Automated ParkingStandard Slotrobotics embodied aicomputer vision17May 26, 2026
Embodied Household TaskALFWorld (test)robotics embodied ai17May 12, 2026
Scene DescriptionWAD (test)computer visionnlp17May 12, 2026
3D Question AnsweringSQA3D (val)3d vision geometrynlp17Jul 3, 2026
Abductive Logical ReasoningQUAILllm chat instructionnlp17May 11, 2026
Unconditional GenerationFineWeb-Edu Mask source 170M-parameter (train)nlp17May 11, 2026
Unconditional GenerationFineWeb-Edu Uniform source 170M-parameter (train)nlp17May 11, 2026
Video Question AnsweringOVO-Benchmultimodalcomputer vision17May 11, 2026
Video Question AnsweringOVO-Bench Backward Tracingmultimodalcomputer vision17May 11, 2026
Video Question AnsweringOVO-Bench Real-Time Visual Perceptionmultimodalcomputer vision17May 11, 2026
Mathematical ReasoningLG-GSM8Kllm chat instructionnlp17May 11, 2026
Deepfake DetectionDaGAN FFHQcomputer visionadversarial safety security17May 11, 2026
Deepfake DetectionDiffSwap FFHQcomputer visionadversarial safety security17May 11, 2026
Deepfake DetectionDeeperForensicscomputer visionadversarial safety security17May 11, 2026
Mathematical ReasoningHMMT25 Nov.llm chat instructionnlp17May 11, 2026
PDE SolvingDarcy Flow 256x256 resolutionmiscellaneous17May 11, 2026
PDE SolvingDarcy Flow 128x128 resolutionmiscellaneous17May 11, 2026
PDE SolvingDarcy Flow 32x32 resolutionmiscellaneous17May 11, 2026
Node ClassificationCora expanded (test)graph17May 11, 2026
Causal DiscoveryDREAM3tabular time series17Jun 12, 2026
Remote Sensing Change DetectionGaza-Change MM v2 (test)computer vision17May 11, 2026
Remote Sensing Change DetectionWHUCD-MMcomputer vision17May 11, 2026