List your company

Research

Benchmarks

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

309,131 benchmarksPage 1839 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Mathematical ReasoningGSM-Symbolicllm chat instructionnlp18Apr 29, 2026
Mathematical ReasoningOmni-MATHllm chat instructionnlp18Apr 29, 2026
Mathematical ReasoningOlympiadBenchllm chat instructionnlp18Apr 29, 2026
Mathematical ReasoningAMC 23llm chat instructionnlp18Apr 29, 2026
Cancer risk predictionEHR-based cancer screening dataset 2016-2023 (test)bio medicaltabular time series18Apr 29, 2026
Certified RobustnessImageNetcomputer visionadversarial safety security18May 26, 2026
Document Understanding, OCR & ChartsTextVQA (val)computer visionnlp18May 12, 2026
Question AnsweringQaspernlp18Apr 28, 2026
Question AnsweringQaspernlp18Apr 28, 2026
Question AnsweringHotpotQAnlp18Apr 28, 2026
Chart-to-code generationChart2NCode Chart2R (test)code developer aibio medical18Apr 28, 2026
General KnowledgeC-Evalllm chat instruction18Jun 30, 2026
Tabular RegressionHousing (test)tabular time series18Apr 28, 2026
Tabular ClassificationMIC (test)tabular time series18Apr 28, 2026
Tabular ClassificationIris (test)tabular time series18Apr 28, 2026
Solar Power ForecastingSolar power forecasting dataset (test)tabular time series18Apr 28, 2026
Circuit RecoveryARC-Cllm chat instruction18Apr 28, 2026
Circuit RecoveryARC-Ellm chat instruction18Apr 28, 2026
Circuit RecoveryArithllm chat instruction18Apr 28, 2026
Classic Discrete ControlMountainCar v0robotics embodied ai18May 29, 2026
Classic Discrete ControlCartPole v1robotics embodied ai18May 29, 2026
General & Complex QADOmnillm chat instructionnlp18Apr 28, 2026
Temporal Question AnsweringTimeQA Easy-modenlpretrieval search rag18Apr 28, 2026
Eigenvalue problem solvingEllipse Dimension: 4900, Precision: 1e-10miscellaneous18Apr 28, 2026
Eigenvalue problem solvingPoisson Dimension 2500 Precision 1e-12miscellaneous18Apr 28, 2026