List your company

Research

Benchmarks

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

309,131 benchmarksPage 1438 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Open-ended generationCARE-prollm chat instruction21May 26, 2026
Regional knowledge and conversational settingsCAREllm chat instruction21May 26, 2026
Camera Control Video GenerationSingle-Effect Camera Control Datasetvideo generation editing21May 26, 2026
Question AnsweringARC Cnlp21Jun 30, 2026
Conformal PredictionImageNet (five repeated splits)tabular time series21May 26, 2026
CalibrationTabular datasetstabular time series21May 26, 2026
Mathematical ReasoningAMC 2023llm chat instructionnlp21May 26, 2026
Mathematical ReasoningAIME 2024llm chat instructionnlp21May 26, 2026
Safety ControllabilitySafety Domainsadversarial safety security21May 26, 2026
Logical ReasoningRule-chaining (test)nlp21May 26, 2026
Constraint SatisfactionGraph Coloring (test)miscellaneous21May 26, 2026
Constraint SatisfactionN-Queens N=8 (test)miscellaneous21May 26, 2026
Logical ReasoningRule-chainingnlp21May 26, 2026
Combinatorial SearchN-Queens N=8miscellaneous21May 26, 2026
MathematicsMinerva Mathnlp21May 26, 2026
Software Vulnerability DetectionOSV-Bench 1.0 (test)code developer aiadversarial safety security21May 26, 2026
Code GenerationCodeContestscode developer ai21May 25, 2026
Code GenerationLiveCodeBenchcode developer ai21May 25, 2026
Code GenerationLiveBenchcode developer ai21May 25, 2026
High-dimensional optimizationMSLRmiscellaneous21May 25, 2026
Video GenerationWan 1.3B (81 frames, 832×480) 2.1video generation editing21Jun 26, 2026
Constrained Path PlanningTextualized Gridworld Long targets (test)robotics embodied ai21May 25, 2026
Constrained Path PlanningTextualized Gridworld Safe targets (test)robotics embodied ai21May 25, 2026
Constrained Path PlanningTextualized Gridworld Short targets (test)robotics embodied ai21May 25, 2026
Fair agent decision makingSchool admission continuousagents tool useadversarial safety security21May 22, 2026