List your company

Research

Benchmarks

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

309,131 benchmarksPage 1250 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
General Question AnsweringNatural Questions (NQ) (test val)nlpretrieval search rag24Feb 26, 2026
Mathematical ReasoningAIME 2025llm chat instructionnlp24Feb 26, 2026
Logical ReasoningEnglishnlp24Feb 26, 2026
Deep researchGAIAmiscellaneous24Mar 24, 2026
Mathematical ReasoningOlympiad Bench (test)llm chat instructionnlp24Apr 9, 2026
Prompt OptimizationPrompt Optimization Benchmarkllm chat instruction24Feb 26, 2026
Automatic Speech RecognitionAISHELL-2speech audio24May 1, 2026
Zero-shot Language Understanding and ReasoningBENCH-PROXY (MMLU, ANLI, HellaSwag, PIQA, SIQA, W.G., ARC-E, ARC-C, C.QA, WSC) (test)llm chat instructionnlp24Feb 26, 2026
MemoryBench TaskMemoryBench Long-Input-Long-Outputllm chat instruction24Feb 26, 2026
MemoryBench TaskMemoryBench Short-Input-Short-Outputllm chat instruction24Feb 26, 2026
MemoryBench TaskMemoryBench Short-Input-Long-Output 1.0llm chat instruction24Feb 26, 2026
Toxicity MitigationREALTOXICITYPROMPTSadversarial safety securitynlp24Feb 26, 2026
Deep-search QAXbench-DeepSearch (test)retrieval search ragnlp24Feb 26, 2026
Deep-search QABrowseComp (test)retrieval search ragnlp24Feb 26, 2026
Machine-Generated Text DetectionReuters ChatGPT-turbonlp24Feb 26, 2026
Machine-Generated Text DetectionReuters ChatGLMnlp24Feb 26, 2026
Machine-Generated Text DetectionReuters Dollynlp24Feb 26, 2026
Machine-Generated Text DetectionReuters ChatGPT splitnlp24Feb 26, 2026
Machine Generated Text DetectionEssay ChatGPT-turbo (test)nlp24Feb 26, 2026
Machine Generated Text DetectionEssay Claude (test)nlp24Feb 26, 2026
Machine Generated Text DetectionEssay ChatGLM (test)nlp24Feb 26, 2026
Machine Generated Text DetectionEssay Dolly (test)nlp24Feb 26, 2026
Machine Generated Text DetectionEssay (ChatGPT) (test)nlp24Feb 26, 2026
Machine Generated Text DetectionEssay GPT4All (test)nlp24Feb 26, 2026
Scientific Table & Figure AnalysisANABENCH (test)tabular time seriescomputer vision+124Feb 26, 2026