List your company

Research

Benchmarks

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

309,131 benchmarksPage 1022 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Concept RecognitionHPA trained on ALDcomputer vision27Feb 26, 2026
Story GenerationNative Story Generation Egyptnlp27Feb 26, 2026
Story GenerationNative Story Generation Indonesianlp27Feb 26, 2026
Story GenerationNative Story Generation China (native)nlp27Feb 26, 2026
Embedding-to-Abstract Reconstruction (emb2abs)PubMedRCT (test)nlp27Feb 26, 2026
Logical ReasoningBBEHnlp27May 21, 2026
Mathematical ReasoningAIME 2025llm chat instructionnlp27Feb 26, 2026
AgenticBrowseCompagents tool use27Feb 26, 2026
Common-sense ReasoningBBHnlp27Feb 26, 2026
CodingLiveCodeBench v6code developer aiCoding on LiveCodeBench v6 performance trend27Jun 16, 2026
Long-context language modelingHELMETllm chat instructionnlp27Feb 26, 2026
Writing flaw detectionBenchMarker Writing - Out of Domain, Humannlp27Feb 26, 2026
Writing flaw detectionBenchMarker Writing - In Domain, NLPnlp27Feb 26, 2026
LLM AlignmentHarmlessnessllm chat instructionadversarial safety security27May 19, 2026
Multidimensional Knapsack ProblemMKPmiscellaneous27Jun 4, 2026
Mathematical ReasoningAMC 2023llm chat instructionnlp27Feb 26, 2026
Traveling Salesman ProblemEuclidean TSP n=500 Uniform distribution in unit square (test)miscellaneous27May 20, 2026
Traveling Salesman ProblemEuclidean TSP n=100 Uniform distribution in unit square (test)miscellaneous27May 20, 2026
Live Streaming Risk AssessmentJune Dataset 1.0 (test)adversarial safety security27Jun 4, 2026
Live Streaming Risk AssessmentMay Dataset 1.0 (test)adversarial safety security27Jun 4, 2026
Verilog GenerationVerilogEval v2code developer ai27Jun 12, 2026
CTR predictionKuaiVideotabular time series27Apr 23, 2026
Classic ControlMountainCar v1.0 (Drift II)robotics embodied ai27Feb 26, 2026
Classic ControlMountainCar v1.0 (Drift I)robotics embodied ai27Feb 26, 2026
Continuous ControlMountainCar Sourcerobotics embodied ai27Feb 26, 2026