List your company

Research

Benchmarks

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

309,131 benchmarksPage 2273 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Question Answering50-question climate adaptation dataset 1.0 (test)nlp16Feb 26, 2026
CodingLiveCodeBenchcode developer ai16Feb 26, 2026
General ReasoningGlobal MMLUllm chat instructionnlp16Feb 26, 2026
SummarizationXL-SUM Target languagenlp16Feb 26, 2026
Machine TranslationFLORES-200 Target languagenlp16Feb 26, 2026
Machine Reading ComprehensionBelebele Source language ennlp16Feb 26, 2026
SummarizationXL-SUM ennlp16Feb 26, 2026
Machine TranslationFLORES-200 Source language ennlp16Feb 26, 2026
Mathematical ReasoningMATH 500llm chat instructionnlp16Feb 26, 2026
Visual ReasoningVisuLogicmultimodalcomputer vision16Jun 2, 2026
Long-context reasoningBABILongllm chat instruction16Jun 23, 2026
Synthetic ReasoningReasoning Primitivesllm chat instructionnlp16Feb 26, 2026
Mathematical ReasoningMath Wordllm chat instructionnlp16Feb 26, 2026
Multi-subject KnowledgeMMLUnlp16May 13, 2026
Relation ExtractionFewRel (test)nlp16Feb 27, 2026
Relation ExtractionWiki ZSL (test)nlp16Feb 27, 2026
Multi-document Question AnsweringMDQAnlpretrieval search rag16Feb 26, 2026
ChatAlpacaEval LC 2llm chat instruction16May 18, 2026
Long-context UnderstandingHELMET 2025llm chat instructionnlp16Feb 26, 2026
Continual LearningSelfRC, TweetQA, and SST sequence SQuAD format (test)miscellaneous16Feb 26, 2026
Code GenerationHumanEval 0-shotcode developer ai16May 1, 2026
Knowledge ReasoningGPQA Diamondnlpgraph16May 8, 2026
Safety EvaluationJailbreakBenchadversarial safety security16Apr 2, 2026
End-to-end TranslationGLTLnlp16Feb 26, 2026
End-to-end TranslationCWnlp16Feb 26, 2026