List your company

Research

Benchmarks

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

309,131 benchmarksPage 1762 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Semantic Textual Similarity (STS)MTEB English 2023 (test)nlpretrieval search rag19Feb 26, 2026
Face VerificationCP-LFWcomputer vision19Feb 26, 2026
Instance SegmentationOV-LVIS v1.0 (val)computer vision19Feb 26, 2026
Code GenerationDS-1000 1.0 (test)code developer ai19Feb 26, 2026
Information RetrievalNQretrieval search rag19Mar 17, 2026
3D Instance SegmentationScanNet (val)3d vision geometrycomputer vision19Feb 26, 2026
Visual Place Recognition17 Placescomputer vision19Feb 26, 2026
LocomotionD4RL Gym-MuJoCo walker2d-medium v2robotics embodied ai19May 19, 2026
Text-to-motion generationKIT (test)computer visionnlp19Apr 10, 2026
Semantic SegmentationCityscapes 1.0 (val 1/2 split)computer vision19Mar 24, 2026
3D Human Pose EstimationSceneEgo 50 (test)3d vision geometrycomputer vision19Feb 26, 2026
Adversarial AttackImageNet-compatibleadversarial safety securitycomputer vision19Apr 7, 2026
Semantic SegmentationPascal VOC 366 labelscomputer vision19Feb 26, 2026
Molecule Design OptimizationTDC DRD3 (test)bio medical19Feb 26, 2026
Job-Shop Scheduling ProblemJSSP 100 instances 10x10 (test)miscellaneous19Feb 26, 2026
Deepfake DetectionDeepfakeTIMIT HQcomputer visionadversarial safety security19May 19, 2026
Deepfake DetectionDeepfakeTIMIT LQcomputer visionadversarial safety security19Feb 26, 2026
Downstream performance predictionYE (Yeast) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionOT (Otto) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionMI (Midas) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionJA (Jannis) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionHO (Housing) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionHI (Hill-Valley) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionHE (Heart) corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026
Downstream performance predictionGE German corrupted with Laplace noisellm chat instructionnlp19Feb 26, 2026