List your company

Research

Benchmarks

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

309,131 benchmarksPage 1924 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Hallucination DetectionFRANKllm chat instructionnlp18Feb 26, 2026
Question AnsweringSimpleQA-verified OODnlp18Feb 26, 2026
Question AnsweringHotpotQA IDnlp18Feb 26, 2026
Question AnsweringNQ IDnlp18Feb 26, 2026
Medical Ethics EvaluationMedES 1.0 (test)bio medicalnlp18Feb 26, 2026
Mathematical ReasoningAIME 25llm chat instructionnlp18Feb 26, 2026
Mathematical ReasoningAIME24llm chat instructionnlp18Feb 26, 2026
Multi-modal Instruction FollowingMM MTBenchllm chat instructionmultimodal18Apr 7, 2026
Node ClassificationProductsgraph18Feb 26, 2026
Spreadsheet UnderstandingSpreadsheetLLM benchmarknlptabular time series18Feb 26, 2026
Long-context Question AnsweringLOCOMO singlellm chat instructionnlp18Jun 5, 2026
Long-context Question AnsweringLOCOMO locomo_openllm chat instructionnlp18Jun 5, 2026
Code GenerationLiveCodeBench v6, LiveCodeBench-ko, HumanEval+, HumanEval+ ko, MBPP+, SciCodecode developer ai18Feb 26, 2026
Interruption HandlingFull-Duplex-Benchllm chat instruction18Apr 15, 2026
Question AnsweringAmbigQAnlp18Feb 26, 2026
Question AnsweringNQnlp18Feb 26, 2026
Question AnsweringBambooglenlp18Feb 26, 2026
Question AnsweringMuSiQuenlp18Feb 26, 2026
Question AnsweringHotpotQAnlp18Feb 26, 2026
Toxicity EvaluationBOLD 23679 prompts (test)adversarial safety securitynlp18Feb 26, 2026
Search RelevanceMinor Language family Qwen2.5 series benchmark (test)retrieval search rag18Feb 26, 2026
Search RelevanceRomance language family Qwen2.5 series benchmark (test)retrieval search rag18Feb 26, 2026
Search RelevanceGermanic language family Qwen2.5 series benchmark (test)retrieval search rag18Feb 26, 2026
Survey GenerationScientific Survey Generation (test)llm chat instructionnlp18Feb 26, 2026
Constrained Machine TranslationSand-Glass Zh-Es (test)nlp18Feb 26, 2026