List your company

Research

Benchmarks

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

309,131 benchmarksPage 1309 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Large Language Model EvaluationMMLU, GSM8K, GPQA, HUMANEVAL, TRUTHFULQA, IFEVALllm chat instruction23Mar 4, 2026
HDR Video Quality AssessmentBeyond8Bits (test)computer vision23Mar 4, 2026
Video Quality AssessmentSFV+HDR (test)computer vision23Mar 4, 2026
Video Quality AssessmentLIVE-HDR (test)computer vision23Mar 4, 2026
Phase retrievalFFHQ 256 x 256computer vision23Jun 30, 2026
Long-Horizon User-Centric Interactionτ2-Benchagents tool usellm chat instruction23Mar 4, 2026
Code-Centric Agent InteractionColBenchagents tool usecode developer ai23Mar 4, 2026
User-Centric Agent InteractionUserGymagents tool usellm chat instruction23Mar 4, 2026
Continual LearningImageNetR 5Smiscellaneous23May 12, 2026
Image ReconstructionMS-COCO 256x256 2017 (val)computer vision23Apr 29, 2026
Document Question AnsweringDUDEnlpcomputer vision23Mar 4, 2026
Multi-way preference rankingEDITREWARD-BENCHllm chat instruction23May 12, 2026
Implicit Concept ErasureRing-A-Belladversarial safety security23May 29, 2026
Short-text ClusteringClinc150 (test)nlp23Feb 27, 2026
Symbolic RegressionLSR-Synth Material Sciencemiscellaneous23Jun 4, 2026
Symbolic RegressionLSR-Synth Physicsmiscellaneous23Jun 4, 2026
Referring Remote Sensing Image SegmentationRefSegRS (val)computer visionnlp23May 26, 2026
Scientific Chart UnderstandingCharXiv 1.0computer visionnlp23Feb 27, 2026
Spatiotemporal predictionHuman3.6M 256x256computer vision3d vision geometry23Feb 26, 2026
Text-to-image generationFLUX.1-schnell 1.0 (dev)image generation editing23Feb 26, 2026
Robotic ManipulationD4RL Kitchen-Partialrobotics embodied ai23Jun 1, 2026
change detectionAvg across SYSU, LEVIR, GVLM, CLCD, OSCDcomputer vision23Feb 26, 2026
Video ReferringVideoRefer-Bench-Dcomputer visionnlp23May 19, 2026
Node ClassificationOgbn-proteins (test)graph23May 25, 2026
Image UnderstandingMMBenchcomputer visionmultimodal23Apr 7, 2026