List your company

Research

Benchmarks

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

309,131 benchmarksPage 1535 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
General Model EvaluationIFEval, MultiIF, MMLU, MMLU-Pro, GPQA-Diamond, HumanEval, MBPP, GSM8K, MATH-500, TheoremQA, CMMLU, CEvalllm chat instructioncode developer ai+120Jun 19, 2026
General Language UnderstandingCMMLU, CEvalnlp20Jun 19, 2026
Mathematical ReasoningGSM8K, MATH 500, TheoremQAllm chat instructionnlp20Jun 19, 2026
General Language UnderstandingMMLU, MMLU-Pro, GPQA-Diamondnlp20Jun 19, 2026
Instruction FollowingIFEval MultiIFllm chat instruction20Jun 19, 2026
3D Vessel ReconstructionWUH3d vision geometrybio medical20Jun 19, 2026
Autonomous Driving Policy EvaluationNAVSIM navhard v2robotics embodied aiadversarial safety security20Jun 19, 2026
Arbitrary-scale super-resolutionDIV2K (val)computer vision20Jun 19, 2026
Arbitrary-scale super-resolutionB100computer vision20Jun 19, 2026
Arbitrary-scale super-resolutionSet14computer vision20Jun 19, 2026
Arbitrary-scale super-resolutionSet5computer vision20Jun 19, 2026
Portfolio optimizationPortfolio optimization Degree 7 (test)tabular time series20Jun 19, 2026
Portfolio optimizationPortfolio optimization Degree 3 (test)tabular time series20Jun 19, 2026
Portfolio optimizationPortfolio optimization Degree 1 (test)tabular time series20Jun 19, 2026
CXR generative fidelityCheXGenBenchbio medicalimage generation editing20Jun 19, 2026
Malware ClassificationDecompiled Binaries Malware Datasetbio medical20Jun 19, 2026
RerankingMTEB 8-task suiteretrieval search rag20Jun 18, 2026
RerankingMTEB eng v2retrieval search rag20Jun 18, 2026
RerankingMTEB multilingual v2retrieval search rag20Jun 18, 2026
Linear RegressionCA housing (val)tabular time series20Jun 18, 2026
Prompt Leaking DefenseLeakBenchadversarial safety security20Jun 18, 2026
Anomaly detectionSALTtabular time series20Jun 18, 2026
Skilled Forgery DetectionMCYTcomputer vision20Jun 18, 2026
Source-Target TransferMultiLoKo source-target aggregationnlp20Jun 18, 2026
Watermark DetectionC4 first 50k textsadversarial safety security20Jun 18, 2026