List your company

Research

Benchmarks

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

309,131 benchmarksPage 2138 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
ClassificationSST-5, MRPC, QNLI, SWAG, IMDB, DBPedia, BoolQ OpenAI large text embeddings (test)computer visionnlp+316Jun 4, 2026
Question Answering and ReasoningNQ, TriviaQA, HotpotQA, and GSM8K Averagellm chat instructionnlp16Jun 4, 2026
Reward ModelingJudgeBenchllm chat instruction16Jun 4, 2026
Image AttributionImageNet-S n=879/914 (val)computer visionnlp16Jun 4, 2026
Image AttributionImageNet n=1000 (val)computer visionnlp16Jun 4, 2026
Image Classification16 Vision Tasks Suite (Cars, DTD, EuroSAT, GTSRB, MNIST, RESISC45, SUN397, SVHN, Caltech101, CUB-200, Flowers102, OfficeHome, Oxford-IIIT Pet, Food101, FER2013, FashionMNIST) ViT-B/32 (test)computer vision16Jun 4, 2026
Scenario GenerationMetaDrivellm chat instruction16Jun 4, 2026
Adversarial AttackLIBERO-Longadversarial safety securitycomputer vision16Jun 4, 2026
Adversarial AttackLIBERO Goaladversarial safety securitycomputer vision16Jun 4, 2026
Adversarial AttackLIBERO-Objectadversarial safety securitycomputer vision16Jun 4, 2026
Adversarial AttackLIBERO Spatialadversarial safety securitycomputer vision16Jun 4, 2026
Robot ManipulationLIBERO Long suiterobotics embodied ai16Jun 4, 2026
Robot ManipulationLIBERO Object suiterobotics embodied ai16Jun 4, 2026
Robot ManipulationLIBERO Spatial suiterobotics embodied ai16Jun 4, 2026
Language ModelingWT (test)nlp16Jun 4, 2026
Language ModelingWT (val)nlp16Jun 4, 2026
Code GenerationHumanEvalcode developer ai16Jun 4, 2026
Adversarial AttackAdvBenchadversarial safety securitycomputer vision16Jun 18, 2026
Graph ClassificationPROTEINS Cross-domaingraph16Jun 4, 2026
Graph ClassificationIMDB-B Cross-domaingraph16Jun 4, 2026
Graph ClassificationDD Cross-domaingraph16Jun 4, 2026
Graph ClassificationCOLLAB Cross-domaingraph16Jun 4, 2026
AD classificationADNI AMY+FDG+TAUbio medicaltabular time series16Jun 4, 2026
AD classificationADNI CT+FDG+TAUbio medicaltabular time series16Jun 4, 2026
AD classificationADNI (CT+AMY+TAU)bio medicaltabular time series16Jun 4, 2026