List your company

Research

Benchmarks

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

309,131 benchmarksPage 1698 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Web NavigationWebArena Lite v2agents tool userobotics embodied ai19May 27, 2026
SummarizationXSumnlp19May 27, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp19May 27, 2026
Code GenerationHumanEvalcode developer ai19May 27, 2026
SummarizationCNN/DMnlp19May 27, 2026
Text GenerationShareGPTnlp19May 27, 2026
Language ModelingWikiText-2nlp19May 26, 2026
Image ClassificationSUN397computer vision19Jun 5, 2026
Speech CodingLibriTTS 16 kHz (test)speech audio19May 27, 2026
Multi-image spatial reasoningSPBench-MVcomputer visionmultimodal19May 26, 2026
Perspective-dependent reasoningViewSpatial-Benchcomputer vision3d vision geometry19May 26, 2026
Out-of-distribution detectionOOD Detection Source LLM GPT-4o (test)computer visiontabular time series19May 26, 2026
Out-of-distribution detectionOOD Detection Source LLM: Claude-3.5-Haiku (test)computer visiontabular time series19May 26, 2026
Out-of-distribution detectionOOD Detection Source LLM: Gemini-2.5-Flash (test)computer visiontabular time series19May 26, 2026
Text-intensive Visual Question AnsweringVQATextmultimodalnlp+119Jun 2, 2026
Multimodal UnderstandingMMTmultimodal19Jul 1, 2026
Medical Time Series ClassificationADFTD (subject-independent)bio medicaltabular time series19May 26, 2026
Competitive ProgrammingICPC-Evalcode developer ai19May 26, 2026
Competitive ProgrammingLiveCodeBench Pro 2025Q2code developer ai19May 26, 2026
Long-horizon agent performanceBrowseCompagents tool usellm chat instruction19May 26, 2026
Offline Reinforcement LearningD4RL walker2d-medium-expert-sparserobotics embodied ai19May 26, 2026
Offline Reinforcement LearningD4RL hopper-medium-expert-sparserobotics embodied ai19May 26, 2026
Offline Reinforcement LearningD4RL halfcheetah-medium-expert-sparserobotics embodied ai19May 26, 2026
Downstream task evaluationLM Evaluation Harness MMLU, ARC, HellaSwag, TruthfulQA, Winogrande, CommonsenseQAnlpcomputer vision+1419May 26, 2026
Individual Treatment Effect EstimationBlog (test)tabular time series19May 26, 2026