List your company

Research

Benchmarks

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

309,131 benchmarksPage 1828 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
First-occurrence disease predictionMGB Prospective 2024bio medicaltabular time series18May 15, 2026
Spatial ReasoningSpatialScore hardnlp18May 15, 2026
Visual Mathematical ReasoningWeMath strictmultimodalcomputer vision+118May 15, 2026
Visual Mathematical ReasoningMathVerse vision-onlymultimodalcomputer vision+118May 15, 2026
Knowledge RetrievalSTaRK-MAG synthetic (test)retrieval search ragnlp18May 15, 2026
Knowledge RetrievalSTaRK-PRIME synthetic (test)retrieval search ragnlp18May 15, 2026
Medical Question AnsweringPubmedQA+HeadQAbio medicalnlp18May 15, 2026
Reinforcement LearningGym MuJoCo + DMC-Hardrobotics embodied ai18May 15, 2026
Reinforcement LearningDMC Hardrobotics embodied ai18May 15, 2026
Reinforcement LearningGym MuJoCorobotics embodied ai18May 15, 2026
Mathematical reasoningGSM8K 100 examplesllm chat instructionnlp18May 15, 2026
Code generationHumanEval (100 examples)code developer ai18May 15, 2026
Open-ended dialogueMT-Bench 80 questionsllm chat instruction18May 15, 2026
Forward PDE SolvingHelmholtzmiscellaneous18Jun 18, 2026
Omnimodal Video-Audio Question AnsweringIMAVB 1.0multimodalcomputer vision+118May 14, 2026
Uncertainty QuantificationGPQA (test)miscellaneous18May 14, 2026
Story CompletionXStoryCloze 1.0 (test)nlp18May 14, 2026
Paraphrase IdentificationPAWS-X 1.0 (test)nlp18May 14, 2026
Table ExplicitationTable Explicitationnlp18May 14, 2026
Precipitation NowcastingMeteoNet 100-minute forecasting 1.0 (test)tabular time series18May 14, 2026
Precipitation NowcastingSEVIR 100-minute forecasting 1.0 (test)tabular time series18May 14, 2026
Traffic JunctionTrafficJunction Largerobotics embodied ai18May 14, 2026
Traffic JunctionTrafficJunction Smallrobotics embodied ai18May 14, 2026
Multi-agent Observation SharingTrafficJunction-Large (TJ-L)robotics embodied aiagents tool use18May 14, 2026
Multi-agent Observation SharingTrafficJunction Smallrobotics embodied aiagents tool use18May 14, 2026