List your company

Research

Benchmarks

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

309,131 benchmarksPage 1004 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Text CompletionText Completionllm chat instruction27Apr 8, 2026
Question AnsweringMathQA, MMLU, HellaSwag, RACE, and CosmosQAnlp27Apr 8, 2026
Visual localizationInLoc DUC1computer vision3d vision geometry27Jul 7, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp27Apr 7, 2026
Token-level hallucination detectionMS COCO image captioning (test)nlpmultimodal27Apr 7, 2026
Sequential RecommendationGrocery Tailtabular time series27Apr 7, 2026
Sequential RecommendationGrocery Overalltabular time series27Apr 7, 2026
Sequential RecommendationBeauty Tailtabular time series27Apr 7, 2026
Sequential RecommendationBeauty Overalltabular time series27Apr 7, 2026
Language SteeringTatoebanlp27Apr 7, 2026
Language SteeringFLORES+, WikiMatrix, and Tatoeba (Averaged)nlp27Apr 7, 2026
Steered Language GenerationFLORES+nlpllm chat instruction27Apr 7, 2026
Language SteeringWikiMatrixnlp27Apr 7, 2026
Multi-Object TrackingnuScenescomputer vision27Jul 7, 2026
Secondary lyophilization process predictionsecondary lyophilization datasetbio medicaltabular time series27Apr 7, 2026
Activation SteeringTONEBANKllm chat instruction27Apr 7, 2026
Diagnostic Report GenerationMIMIC-CXR 14 (test)bio medicalnlp27Apr 20, 2026
Articulated Object Geometry ReconstructionPartNet-Mobility source and target3d vision geometrycomputer vision27Apr 6, 2026
Articulated Motion EstimationPartNet-Mobility (source and target)3d vision geometrycomputer vision27Apr 6, 2026
Audio-visual NavigationReplica 1.0 (Unheard)robotics embodied aispeech audio+127Apr 8, 2026
Unconditional Text GenerationROCStoriesnlp27May 18, 2026
Natural Language InferenceChaosNLI S easy (test)nlp27Apr 3, 2026
Natural Language InferenceChaosNLI S_amb (test)nlp27Apr 3, 2026
Natural Language InferenceChaosNLI (test)nlp27Apr 3, 2026
Red Teaming AttackHarmBench (test)adversarial safety security27Apr 3, 2026