List your company

Research

Benchmarks

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

309,131 benchmarksPage 1495 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
CodingCoverage (test)code developer ai21Feb 26, 2026
ClassificationCoverage (test)computer visionnlp+321Feb 26, 2026
SummarizationCoverage dataset (test)nlp21Feb 26, 2026
Knowledge EditingCounterfact Full (test)nlpllm chat instruction21Feb 26, 2026
Knowledge EditingZsRE (evaluation)nlpllm chat instruction21Feb 26, 2026
Multi-hop Question AnsweringIIRCnlpretrieval search rag21Jul 3, 2026
Image ClassificationCDDB-Hard (test)computer vision21Feb 26, 2026
Image CaptioningMSCOCO (random sampling of 500 instances)multimodalcomputer vision+121Feb 26, 2026
Question AnsweringHotpotQA December 2018 Wikipedia dump (test)nlp21Jun 26, 2026
Question AnsweringNQ, TriviaQA, and WebQ (test)nlp21Feb 26, 2026
Long-context understandingLongBench v1 (test)llm chat instructionnlp21Feb 26, 2026
Instruction FollowingAlpaca (test)llm chat instruction21Apr 30, 2026
Novel View SynthesisNeRF Synthetic 800 x 800 (test)3d vision geometry21Feb 26, 2026
Novel View SynthesisReal Forward-facing 640 x 960 (test)3d vision geometry21Feb 26, 2026
Video Understanding ReasoningMLVUcomputer vision21Apr 10, 2026
Reading ComprehensionRACEnlp21Jun 4, 2026
Long-form generationLongBench Write-enllm chat instructionnlp21Jun 9, 2026
Image DenoisingCBSD68 sigma=50computer vision21Feb 26, 2026
Image DenoisingCBSD68 sigma=25computer vision21Feb 26, 2026
Image DenoisingCBSD68 sigma=15computer vision21Feb 26, 2026
Jailbreak DefenseAggregate Benchmarksadversarial safety security21Feb 26, 2026
Jailbreak DefenseGPTFuzzeradversarial safety security21Feb 26, 2026
Jailbreak DefenseReNeLLM & DeepInception Averageadversarial safety security21Feb 26, 2026
Fingerprint VerificationWizardMath-7B V1.0computer vision21Feb 26, 2026
Video Question AnsweringDeVE-QA (test)multimodalcomputer vision21Feb 26, 2026