List your company

Research

Benchmarks

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

309,131 benchmarksPage 1441 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Mathematical ReasoningMATH 500llm chat instructionnlp21May 19, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp21May 19, 2026
Adversarial AttackAdvBench 80/20 (test)adversarial safety securitycomputer vision21May 19, 2026
Machine UnlearningCIFAR-100 50% random data removaladversarial safety security21May 19, 2026
Machine UnlearningCIFAR-100 (10% random data removal)adversarial safety security21May 19, 2026
Item-to-item retrievalE-commerce dataset (test)retrieval search rag21May 19, 2026
Research TaskLiveResearchBench (LRB)miscellaneous21May 19, 2026
Research TaskDeepResearchBench (DRB)miscellaneous21May 19, 2026
Agent TaskPinchBench (PB)agents tool userobotics embodied ai21May 19, 2026
General-domain capability retentionAIME-2024, MATH-500, GSM8K, HumanEval, MMLUllm chat instructioncode developer ai+121May 19, 2026
Arithmetic function acquisitionKGFUNC UNSEENnlp21May 19, 2026
Arithmetic function acquisitionKGFUNC (test)nlp21May 19, 2026
Closed-book Question AnsweringSimpleQA (train)nlp21May 19, 2026
General capability retentionHeld-out capability averagellm chat instructionnlp21May 19, 2026
Code generationHumanEvalcode developer ai21May 19, 2026
Retrieval-augmented recallKGFACT RETRIEVALretrieval search rag21May 19, 2026
Closed-book recallKGFACT SMALL (train)llm chat instructionnlp21May 19, 2026
Unsupervised Outlier Model Selection39 tabular benchmark datasetstabular time series21May 19, 2026
Real-world Multimodal UnderstandingRealWorldQAmultimodalcomputer vision+121May 27, 2026
Arrhythmia classificationVitalDBbio medicaltabular time series21May 19, 2026
Arrhythmia classificationINCARTbio medicaltabular time series21May 19, 2026
Arrhythmia classificationMIT-BIH-SUPbio medicaltabular time series21May 19, 2026
Arrhythmia classificationMIT-BIHbio medicaltabular time series21May 19, 2026
Counterfactual ExplanationsCOMPAStabular time series21Jun 1, 2026
Reentrant Network ModelingReentrant Networkmiscellaneous21May 19, 2026