List your company

Research

Benchmarks

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

309,131 benchmarksPage 623 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Source Code Watermark Extraction RobustnessCodeNet D40 (evaluation)code developer ai36Jul 8, 2026
Source Code Watermark Extraction RobustnessCodeNet D32 (evaluation)code developer ai36Jul 8, 2026
Watermark Detection RobustnessC4adversarial safety securitynlp36Jul 8, 2026
Code GenerationHE+code developer ai36Jul 7, 2026
Interactive Agent TaskALFWorldagents tool userobotics embodied ai36Jul 7, 2026
Code GenerationLiveCodeBenchcode developer ai36Jul 3, 2026
Six-class anatomical-region classificationMayo 2020 (test)computer visionbio medical36Jul 3, 2026
Question Answering2WikiMultihopQAnlp36Jul 2, 2026
Question AnsweringMuSiQuenlp36Jul 2, 2026
Question AnsweringHotpotQAnlp36Jul 2, 2026
Multihop Question Answering2WikiMultihopQAnlpretrieval search rag36Jul 2, 2026
Multihop Question AnsweringMuSiQuenlpretrieval search rag36Jul 2, 2026
Multihop Question AnsweringHotpotQAnlpretrieval search rag36Jul 2, 2026
LLM Prefill throughputLLM Prompt Length 2048 (pp2048)llm chat instruction36Jul 2, 2026
LLM Prefill throughputLLM Prompt Length 1024llm chat instruction36Jul 2, 2026
Multiple choice question visual question answeringMultiple choice question (MCQ) visual question answering (VQA) benchmarks Averagemultimodalcomputer vision+136Jul 1, 2026
Image ClassificationAircraftcomputer vision36Jul 1, 2026
Image ClassificationStanfordCarscomputer vision36Jul 1, 2026
Image ClassificationPetscomputer vision36Jul 1, 2026
Mathematical ReasoningGSM8Kllm chat instructionnlp36Jul 7, 2026
Downstream AUROC performance evaluationCamelyon 17bio medicaltabular time series36Jun 30, 2026
Covariance Test-Time AdaptationTerratabular time series36Jun 30, 2026
Covariance Test-Time AdaptationVisDA 2017tabular time series36Jun 30, 2026
Language Model Training EfficiencyFineWebllm chat instruction36Jun 30, 2026
LocalizationBlackbird clov, patr, thri, wint, amp, dice, half, sid trajectories (test)computer vision36Jun 30, 2026