List your company

Research

Benchmarks

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

309,131 benchmarksPage 778 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Visual Jailbreaking AttackHADESadversarial safety securitymultimodal32Mar 4, 2026
Visual Jailbreaking AttackAdvBenchadversarial safety securitymultimodal32Mar 4, 2026
Commonsense ReasoningCommonsense Reasoning (PIQA, WinoG., HellaS., BoolQ, SIQA, OBQA) (test)nlp32Feb 27, 2026
Image ClassificationStanfordCars, DTD, EuroSAT, GTSRB, RESISC45, SUN397, SVHNcomputer vision32Jul 1, 2026
Text Classification20News (test)nlp32Mar 11, 2026
Time Series ForecastingETTm1 v1 (test)tabular time series32Apr 28, 2026
Online InferenceShareGPTllm chat instruction32May 27, 2026
Multilingual UnderstandingCMMLUnlp32May 27, 2026
Membership Inference AttackGitHubadversarial safety security32Mar 23, 2026
Multivariate Time-series ForecastingTraffictabular time series32Feb 26, 2026
Multivariate Time-series ForecastingElectricitytabular time series32Feb 26, 2026
Contributor AttributionCIFAR-20computer vision32Feb 26, 2026
Mathematical ReasoningMinervallm chat instructionnlp32Mar 4, 2026
Instruction FollowingAlpacaEval 2 (val)llm chat instruction32Jun 4, 2026
Multi-class ClassificationEOL (test)tabular time series32Feb 26, 2026
Multi-class ClassificationIF (test)tabular time series32Feb 26, 2026
Multi-class ClassificationJV (test)tabular time series32Feb 26, 2026
Binary ClassificationEmployee (test)tabular time series32Feb 26, 2026
Binary ClassificationKC1 (test)tabular time series32Feb 26, 2026
Conversational Question AnsweringCOQA zero-shot (test)nlpllm chat instruction32Feb 26, 2026
Mathematics Question AnsweringGSM8K zero-shot (test)nlpllm chat instruction32Feb 26, 2026
Causal DiscoverySynthetic n=1000, |E|=2000, sample size=1000tabular time series32Feb 26, 2026
RegressionHousingtabular time series32May 12, 2026
Zero-shot Question Answering and ReasoningLM-Eval-Harness Suite (PIQA, HellaSwag, LAMBADA, ARC-e, ARC-c, SciQ, Race, MMLU) zero-shotnlpllm chat instruction32Feb 26, 2026
RecommendationBabytabular time series32Apr 7, 2026