List your company

Research

Benchmarks

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

309,131 benchmarksPage 2649 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
CoordinationOvercooked Cramped Room layout v1robotics embodied ai14May 13, 2026
Cross-view Geo-localizationDenseUAV Satellite → Dronecomputer vision14May 15, 2026
Cross-view Geo-localizationDenseUAV (test)computer vision14May 13, 2026
Instruction-followingInstruction-following datasetllm chat instruction14May 13, 2026
Software Engineering Issue SolvingSWE-bench Verifiedcode developer ai14May 13, 2026
Software EngineeringSWE-bench Multilingualcode developer ai14May 13, 2026
DeblurringImageNet (test)computer vision14May 13, 2026
Trajectory PredictionSDD (Stanford Drone Dataset) original (test)robotics embodied aitabular time series14May 13, 2026
Knowledge-intensive Question AnsweringGPQAnlpretrieval search rag14May 13, 2026
Text-based agent interactionTextWorld Cooking (test)agents tool usellm chat instruction14May 13, 2026
Text-based agent interactionTextWorld Treasure (test)agents tool usellm chat instruction14May 13, 2026
Text-based agent interactionTextWorld Quest (test)agents tool usellm chat instruction14May 13, 2026
Multiple Exposure CorrectionSICE Over 4 (test)computer vision14May 13, 2026
Multiple Exposure CorrectionSICE Under 4 (test)computer vision14May 13, 2026
Abdominal SegmentationHepatic Vessel Tumor MSD (test)computer vision14May 13, 2026
Abdominal Multi-organ SegmentationAMOS 2022 (test)bio medicalcomputer vision14May 13, 2026
Medical Image SegmentationBrain Tumorbio medicalcomputer vision14May 13, 2026
Organ SegmentationFLARE Externalcomputer vision14May 13, 2026
Organ SegmentationFLARE Internalcomputer vision14May 13, 2026
RegressionTabReD Regressiontabular time series14May 13, 2026
Emergence attribution runtime analysisMythosmiscellaneous14May 13, 2026
Human Subjective EvaluationNarrative Detective Stories Human Subjective Evaluation (test)llm chat instruction14May 13, 2026
Integer Linear ProgrammingISmiscellaneous14May 13, 2026
Agentic Workflow Hijacking Vulnerability Detectiongoogle-github-actions/run-gemini-cliagents tool useadversarial safety security+114May 13, 2026
Agentic Workflow Hijacking Vulnerability Detectionask-bonk GitHub Actionagents tool useadversarial safety security+114May 13, 2026