List your company

Research

Benchmarks

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

309,131 benchmarksPage 1827 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image GenerationCIFAR-10image generation editing18May 18, 2026
Deep ResearchSQA v2miscellaneous18May 18, 2026
Image Deconvolutionset3c butterfly image (test)computer vision18May 18, 2026
Long-context evaluationLongBench (test)llm chat instruction18May 18, 2026
Named Entity RecognitionDynamicNER 1.0nlp18May 18, 2026
Corallite SegmentationAstraeiformis Task C: diff. speciescomputer vision18May 15, 2026
Corallite SegmentationNaturalis 6781 Ortho #1003 Task B: same speciescomputer vision18May 15, 2026
Corallite SegmentationNaturalis 6781 Growth #2499 Task A: same axiscomputer vision18May 15, 2026
Execution AccuracyBFCL v2code developer ai18May 15, 2026
GUI agent successWebVoyager (test)agents tool usellm chat instruction18May 15, 2026
Pixel GroundingEgoHOS Out-of-distribution (test)computer vision18May 15, 2026
State Estimation3-variable simulated dataset (No. 2) with frequent transitions v1 (test)tabular time series18May 15, 2026
Forecasting and state estimation10-variable simulated dataset (infrequent transitions)tabular time series18May 15, 2026
Best feasible prompt identificationXSumllm chat instruction18May 15, 2026
Zero-shot Image ClassificationCIFAR-10computer vision18May 15, 2026
Zero-shot Image ClassificationObjectNetcomputer vision18May 15, 2026
Zero-shot Image ClassificationSTLcomputer vision18May 15, 2026
Zero-shot Image ClassificationFoodcomputer vision18May 15, 2026
Machine UnlearningImageNet-1K All Classesadversarial safety security18May 15, 2026
Machine UnlearningImageNet-1K Target Classadversarial safety security18May 15, 2026
Machine UnlearningObjectNetadversarial safety security18May 15, 2026
Machine UnlearningSTLadversarial safety security18May 15, 2026
Machine UnlearningFoodadversarial safety security18May 15, 2026
Machine UnlearningCIFAR-10adversarial safety security18May 15, 2026
Complex Controlcomplex-control target suite (test)robotics embodied ai18May 15, 2026