List your company

Research

Benchmarks

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

309,131 benchmarksPage 1572 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multimodal Question AnsweringMMQAmultimodalnlp+120May 1, 2026
Feature InversionDogscomputer visionimage generation editing20May 1, 2026
Feature InversionPetscomputer visionimage generation editing20May 1, 2026
Feature InversionCUB-200computer visionimage generation editing20May 1, 2026
Feature InversionImageNetcomputer visionimage generation editing20May 1, 2026
Untargeted Adversarial AttackStanford Carsadversarial safety security20May 1, 2026
Untargeted Adversarial AttackCUB 200adversarial safety security20May 1, 2026
LLM Safety EvaluationAymara Risk and Responsibility Matrix 10 Domainsadversarial safety securityllm chat instruction20May 1, 2026
Binary classificationCHB_MIT 2-Class (test)tabular time series20May 13, 2026
Semantic SegmentationURTF (val)computer vision20Apr 30, 2026
BRDF ReconstructionMERL held-out (test)3d vision geometrycomputer vision20Apr 30, 2026
ClassificationCamelyoncomputer visionnlp+320Apr 30, 2026
ClassificationCamelyon (test)computer visionnlp+320Apr 30, 2026
Knowledge boundary assessmentV-Idk 3,000 samples (test)llm chat instruction20Apr 30, 2026
Online Conversion OptimizationCriteo Uplift 100K users (held-out set)tabular time series20Apr 30, 2026
Text Classification20NGnlp20Jun 24, 2026
Human Activity RecognitionUSCHAD (held-out)computer vision20Apr 29, 2026
Super Resolution (SR x4)FFHQ 256x256-1Kcomputer vision20Apr 29, 2026
Voice EvaluationVoiceBenchspeech audio20Jul 7, 2026
General ReasoningAverage (MATH500, OlympiadBench, Minerva, MMLU, GSM8K)llm chat instructionnlp20Apr 28, 2026
Offline Black-box OptimizationDesign-bench 100-th percentilemiscellaneous20Apr 28, 2026
6-DoF object pose trackingSimulated Event Datasetscomputer vision3d vision geometry20Apr 28, 2026
Interactive Decision MakingScienceWorld Seen (val)robotics embodied ai20Apr 28, 2026
Radiology Report GenerationRadiology Report Generation Dataset 1,000 image (random sample)computer visionnlp+120Apr 28, 2026
LLM-as-a-JudgeHigh-contrast response pairsllm chat instruction20Apr 28, 2026