List your company

Research

Benchmarks

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

309,131 benchmarksPage 2364 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Make SandwichBestMan Easyrobotics embodied ai15Jun 16, 2026
Pack ObjectsBestMan Hardrobotics embodied ai15Jun 16, 2026
Pack ObjectsBestMan (Medium)robotics embodied ai15Jun 16, 2026
Pack ObjectsBestMan Easyrobotics embodied ai15Jun 16, 2026
Open-ended Video Question AnsweringNExTQA (test)multimodalcomputer vision15Jun 16, 2026
Open-ended Video Question AnsweringNExTQA (val)multimodalcomputer vision15Jun 16, 2026
Multimodal UnderstandingAI2D, POPE, TextVQA, OKVQA, VizWiz, COCO Caption, NoCaps, and RealWorldQA Averagemultimodal15Jun 15, 2026
RegressionUCI Winetabular time series15Jun 25, 2026
RegressionUCI Powertabular time series15Jun 25, 2026
Agentic CodingDialo-SWE-Benchagents tool usecode developer ai15Jun 15, 2026
Multi-Agent Reinforcement LearningCAGE Challenge 4 (test)robotics embodied ai15Jun 15, 2026
Image ClassificationTiny-ImageNetcomputer vision15Jun 15, 2026
Network Event Evolution SimulationNet-E GLA v2 6.5M (test)tabular time series15Jun 12, 2026
Image EditingGIE-Benchimage generation editing15Jun 12, 2026
Image EditingMagicBrushimage generation editing15Jun 12, 2026
Aspect-level pluralism evaluationReval book reviews (evaluation)nlp15Jun 12, 2026
User Interface ReasoningUXBenchcomputer visionnlp15Jun 12, 2026
Spatio-temporal forecastingPEMS07 (test)tabular time series15Jun 12, 2026
Spatio-temporal forecastingPEMS04 (test)tabular time series15Jun 12, 2026
Spatio-temporal forecastingPEMS03 (test)tabular time series15Jun 12, 2026
Terminal Task ExecutionTerminal-Bench 2.0agents tool use15Jun 24, 2026
Lifelong UnlearningMLUBench Task Cadversarial safety security15Jun 12, 2026
LLM Judging AgreementReasoning Agreement Benchmark 500-sample human-annotatedllm chat instruction15Jun 12, 2026
LLM Judging AgreementReasoning Agreement Benchmark 2,500 samplesllm chat instruction15Jun 12, 2026
Visual Fidelity EvaluationTACO and Aria Datasetcomputer vision15Jun 12, 2026