List your company

Research

Benchmarks

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

309,131 benchmarksPage 2245 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Abstractive SummarizationXSum (val)nlp16Feb 26, 2026
Unconditional GenerationFFHQ 64 x 64nlp16Feb 26, 2026
Language ModelingOpen LLM Leaderboard & General Ability Benchmarks (MMLU-P, GPQA, BBH, MATH, MuSR, IFEval, ARC, Hellaswag, PIQA, BoolQ, WinoGrande, COPA, OpenBookQA, SciQ) unified (test)nlp16Feb 26, 2026
2D semantic segmentationnuImages (full)computer vision16Feb 26, 2026
2D semantic segmentationnuScenes (night)computer vision16Feb 26, 2026
2D semantic segmentationnuScenes day-raincomputer vision16Feb 26, 2026
2D semantic segmentationnuScenes day-clearcomputer vision16Feb 26, 2026
2D semantic segmentationnuScenes (full)computer vision16Feb 26, 2026
2D monocular depth estimationnuScenes fullcomputer vision3d vision geometry16Feb 26, 2026
Mathematical ReasoningMATH (test)llm chat instructionnlp16Feb 26, 2026
Mathematical ReasoningGSM8K (test)llm chat instructionnlp16Feb 26, 2026
Survival AnalysisTCGA-SKCMtabular time series16Mar 12, 2026
Referring Expression RetrievalRefCOCO (val)computer visionnlp16Feb 26, 2026
Logical ReasoningLogical Reasoning Datasets Balancednlp16Feb 26, 2026
Logical ReasoningLogical Reasoning Datasets Unbalancednlp16Feb 26, 2026
Quality ControlFetal brain MRI SRR Leave-one-site-out (out-of-domain)bio medicalcomputer vision16Feb 26, 2026
Question AnsweringARC Challengenlp16Feb 26, 2026
Question AnsweringCommonsenseQAnlp16Feb 26, 2026
Question AnsweringHotpotQAnlp16Feb 26, 2026
Question AnsweringCoQAnlp16Feb 26, 2026
Question AnsweringWeb Questionsnlp16Feb 26, 2026
Question AnsweringTriviaQAnlp16Feb 26, 2026
Bivariate Causal DiscoveryTübingentabular time series16Feb 26, 2026
Missing Data ImputationeICU Collaborative Research Database Simulation of Blockwise Missing Data (n=5000, p=40)tabular time series16Feb 26, 2026
Conformal PredictionSynthetic Data sample size 5000 (test)tabular time series16Feb 26, 2026