List your company

Research

Benchmarks

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

309,131 benchmarksPage 1435 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Logical ReasoningKK 6–8 ppl.nlp21Jun 2, 2026
Logical ReasoningKK 4–5 ppl.nlp21Jun 2, 2026
Logical ReasoningKK 2–3 ppl.nlp21Jun 2, 2026
Hallucination DetectionSQuAD 2 (test)llm chat instructionnlp21Jun 2, 2026
RefusalMuSiQue Unllm chat instructionadversarial safety security21Jun 2, 2026
FaithfulnessConFiQAbio medicalnlp21Jun 2, 2026
Multi-hop ReasoningTAT-QAnlpllm chat instruction21Jun 2, 2026
Common Sense ReasoningBBH Sports Understandingnlp21Jun 2, 2026
Mathematical ReasoningHMMT25llm chat instructionnlp21Jun 2, 2026
Mathematical ReasoningHMMT25llm chat instructionnlp21Jun 2, 2026
Mathematical ReasoningAIME 26llm chat instructionnlp21Jun 2, 2026
Long-video understandingOVOBench Real-Timecomputer vision21Jun 1, 2026
Binary ClassificationWisconsin Breast Cancertabular time series21Jul 7, 2026
Long Video UnderstandingVideoMME Overall (w/o sub.) 2025computer vision21Jun 1, 2026
Remaining Useful Life EstimationC-MAPSS FD004 (test)tabular time series21Jun 1, 2026
Remaining Useful Life EstimationC-MAPSS FD003 (test)tabular time series21Jun 1, 2026
Single-Hop Search-augmented Question AnsweringPopQAretrieval search ragnlp21Jun 11, 2026
Single-Hop Search-augmented Question AnsweringTriviaQAretrieval search ragnlp21Jun 11, 2026
Single-Hop Search-augmented Question AnsweringNQretrieval search ragnlp21Jun 11, 2026
Metric Depth EstimationETH3D3d vision geometry21Jun 1, 2026
Question AnsweringSQuADnlp21Jun 1, 2026
Language UnderstandingMMLUnlp21Jun 1, 2026
Spatial ReasoningAll-Angles Benchnlp21May 29, 2026
Code ExecutionLive Code Executioncode developer ai21May 29, 2026
Code GenerationLive Code Generationcode developer ai21May 29, 2026