List your company

Research

Benchmarks

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

309,131 benchmarksPage 943 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Classificationcoimbracomputer visionnlp+328Apr 10, 2026
Classificationbloodcomputer visionnlp+328Apr 10, 2026
Multi-hop Question AnsweringMARCHnlpretrieval search rag28Apr 10, 2026
Prompt Injection AttackDirect Scenarioadversarial safety securityagents tool use28Apr 10, 2026
Multimodal Question AnsweringSUPERGLASSES 1.0 (Leaderboard)multimodalnlp+128Apr 10, 2026
Image GenerationImageNet 256x256image generation editing28Jun 5, 2026
Medical Image Enhancement446 Patients (external)computer visionbio medical28Apr 10, 2026
Adversarial AttackPalmprint Dataset Hold-out Transfer Setup (unseen target model)adversarial safety securitycomputer vision28Apr 10, 2026
Adversarial AttackIITD transfer from Tongji (test)adversarial safety securitycomputer vision28Apr 10, 2026
Image ClassificationCIFAR-100computer vision28Apr 10, 2026
Image ClassificationCIFAR-10computer vision28Apr 10, 2026
Probed Adversary Evaluation792 Privacy Evaluation Scenarios final benchmark 1.0adversarial safety security28Apr 9, 2026
Jailbreak Attempt ForgettingHarm Jailbreak 2adversarial safety security28Apr 8, 2026
Jailbreak Attempt ForgettingJB-1 Jailbreak Harm-1adversarial safety security28Apr 8, 2026
Harmful Question ForgettingHarm-2 GPTFUZZER WildAttackadversarial safety securityllm chat instruction28Apr 8, 2026
Harmful Question ForgettingHarm-1 GPTFUZZER WildAttackadversarial safety securityllm chat instruction28Apr 8, 2026
Mathematical ReasoningMathQAllm chat instructionnlp28Apr 8, 2026
Mathematical ReasoningMATHllm chat instructionnlp28Apr 8, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp28Apr 8, 2026
Safety EvaluationHarmful and Jailbreak datasetsadversarial safety security28Apr 8, 2026
Medical SummarizationMeQSumbio medicalnlp28Apr 8, 2026
Question AnsweringMedical Multiple Choice (MedQA, PubMedQA, MedMCQA, HeadQA)nlp28Apr 8, 2026
Visual Question AnsweringPMC-VQAmultimodalcomputer vision+128Jun 11, 2026
Traffic Signal ControlHangzhou (HZ-1)robotics embodied ai28Apr 29, 2026
Question AnsweringStrategyQA, MMLU, and HotpotQA Combinednlp28Apr 8, 2026