List your company

Research

Benchmarks

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

309,131 benchmarksPage 632 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Structured Distribution SamplingOOD distribution families Bernoulli, Poisson, Maxwell, TruncNorm, Chi, and Weibull (Held-out)miscellaneous36May 13, 2026
Patience-discounted reward evaluationNoveltyBenchrobotics embodied ai36May 13, 2026
Random-generation diversity evaluationOpen-ended random generationllm chat instruction36May 13, 2026
Question AnsweringOverall (NQ, PopQA, 2WikiQA, Musique, LOCOMO) (test)nlp36May 12, 2026
Conversation Question AnsweringLOCOMO (test)retrieval search ragnlp36May 12, 2026
Simple Question AnsweringPopQA (test)retrieval search ragnlp36May 12, 2026
Simple Question AnsweringNQ* (test)retrieval search ragnlp36May 12, 2026
Bandit OptimizationSetting 2miscellaneous36May 12, 2026
Bandit OptimizationSetting 1miscellaneous36May 12, 2026
Traitor win probability estimationThe Traitors Game Small configurations Migdał value based (n <= 11)llm chat instruction36May 12, 2026
Image ClassificationCIFAR-10 8000 images (test)computer vision36May 12, 2026
Sequential Model EditingZsRE T = 300nlp36May 12, 2026
Sequential Model EditingCounterFact T = 300nlp36May 12, 2026
Language ModelingLlama decoder 10Mnlp36May 12, 2026
Multimodal time-series forecastingAgriculture textual-numerical time-series datasettabular time seriesmultimodal36May 12, 2026
ClassificationDevnagari dev (test)computer visionnlp+336May 12, 2026
Math ReasoningOlympiad Benchllm chat instructionnlp36May 12, 2026
Macro-average Exact MatchShellOps-Procode developer ai36May 11, 2026
Robotic ManipulationRoboTwin (random-scene)robotics embodied ai36May 11, 2026
RelocalizationGrass-Slope Scene3d vision geometrycomputer vision36May 11, 2026
Modular AdditionModular Addition Token Embeddingllm chat instruction36May 11, 2026
Modular AdditionModular Addition Angular Embedding (test)llm chat instruction36May 11, 2026
Causal DiscoveryLorenz-96tabular time series36May 11, 2026
ECG ClassificationCODE-15% (test)bio medicaltabular time series36May 11, 2026
ECG ClassificationMIMIC-IV-ECG (test)bio medicaltabular time series36May 11, 2026