List your company

Research

Benchmarks

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

309,131 benchmarksPage 2157 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
PMI ranking estimationChaosNLI (500 held-out pairs)nlp16May 22, 2026
PMI ranking estimationWords (500 held-out pairs)nlp16May 22, 2026
Knowledge-intensive Question AnsweringOpenSciencenlpretrieval search rag16May 22, 2026
Text-to-Image Generationtext-to-image 2Mimage generation editing16May 22, 2026
LLM PretrainingC4llm chat instruction16May 22, 2026
Code GenerationLCBcode developer ai16May 22, 2026
Question AnsweringGPQAnlp16May 22, 2026
Mathematical ReasoningAIMEllm chat instructionnlp16May 22, 2026
Transferable Adversarial AttackKimi K2.5adversarial safety security16May 22, 2026
Transferable Adversarial AttackLlama 11B-V 3.2adversarial safety security16May 22, 2026
Transferable Adversarial AttackGLM 4.6Vadversarial safety security16May 22, 2026
Targeted AttackGemini 1.5-pro 2.5-flash (test)adversarial safety security3d vision geometry16May 22, 2026
Human Correlation for Image Captioning EvaluationCOMcomputer visionnlp16May 22, 2026
Human Correlation for Image Captioning EvaluationEX-8Kcomputer visionnlp16May 22, 2026
Human Correlation for Image Captioning EvaluationPolariscomputer visionnlp16May 22, 2026
Human Correlation for Image Captioning EvaluationVICRcomputer visionnlp16May 22, 2026
Cooperative Perception Object DetectionMesh Adv. HOLLOW (test)computer vision16May 22, 2026
ReasoningARC Minillm chat instructionnlp16Jun 26, 2026
Entity Regression (item-sales)rel-hmtabular time series16May 25, 2026
Atmospheric Turbulence MitigationATSyn-dynamic (Strong)computer vision16May 28, 2026
Atmospheric Turbulence MitigationATSyn-dynamic Weakcomputer vision16May 28, 2026
Tone-controlled captioningRoadTones Eval 1.0 (test)computer visionnlp16May 21, 2026
Tracking Shuffled ObjectsTracking Shuffled Objects 5 objects (test)computer vision16May 21, 2026
Logical DeductionLogical Deduction 5 objects (test)nlp16May 21, 2026
Robotic ManipulationRLBenchrobotics embodied ai16Jul 9, 2026