List your company

Research

Benchmarks

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

309,131 benchmarksPage 1201 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Longitudinal ClassificationTalkLife (80/20)tabular time series24Apr 21, 2026
Longitudinal ClassificationLRS (80/20)tabular time series24Apr 21, 2026
Longitudinal ClassificationAnnoMI (80/20)tabular time series24Apr 21, 2026
Multi-task ReasoningAverage Out-of-domainllm chat instructionnlp24Apr 21, 2026
Code ReasoningSuperGPQA Code SGPQA-1kcode developer ainlp24Apr 21, 2026
Code ReasoningR-Bench-T Codecode developer ainlp24Apr 21, 2026
Code ReasoningOJBenchcode developer ainlp24Apr 21, 2026
Math ReasoningSuperGPQA SGPQA-1k Mathllm chat instructionnlp24Apr 21, 2026
Math ReasoningR-Bench-T Mathllm chat instructionnlp24Apr 21, 2026
Math ReasoningOlympiadllm chat instructionnlp24Apr 21, 2026
Fuel property predictionFuel RON (10-fold cross-validation)tabular time seriesbio medical24Apr 20, 2026
Medical Report GenerationUltrasound Averagebio medicalnlp24Apr 20, 2026
Medical Report GenerationUltrasound Kidneybio medicalnlp24Apr 20, 2026
Medical Report GenerationUltrasound Gynecologybio medicalnlp24Apr 20, 2026
Medical Report GenerationUltrasound Breastbio medicalnlp24Apr 20, 2026
Hyperspectral Image ClassificationHSI-Benchmark (test)computer vision24Apr 20, 2026
Pathological Image ClassificationCRCcomputer visionbio medical24Apr 20, 2026
Pathological Image ClassificationMHISTcomputer visionbio medical24Apr 20, 2026
Pathological Image ClassificationCAM16computer visionbio medical24Apr 20, 2026
ClassificationSmoking Datasetcomputer visionnlp+324Apr 20, 2026
Jailbreak DefenseJailbreak Attack Suiteadversarial safety security24Apr 20, 2026
Jailbreak Defensejailbreak defense datasetadversarial safety security24May 26, 2026
Web API RecommendationProgrammableWeb (test)retrieval search ragcode developer ai24Apr 20, 2026
Interactive Decision-makingWebShoprobotics embodied ai24Apr 16, 2026
Interactive Decision-makingTextWorldrobotics embodied ai24Apr 16, 2026