List your company

Research

Benchmarks

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

309,131 benchmarksPage 1934 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Topic ModelingNewsgroup Sciencenlp18Feb 26, 2026
Retrieval-Augmented GenerationLOFT and ICR2 Combinedretrieval search ragnlp18Feb 26, 2026
Science Question AnsweringARC randomly sampled 400 instances (test)nlpbio medical18Feb 26, 2026
Mathematical ReasoningGSM8K randomly sampled 400 instances (test)llm chat instructionnlp18Feb 26, 2026
Rationale GenerationSHINESllm chat instructionnlp18Feb 26, 2026
Self-harm ClassificationSHINESnlp18Feb 26, 2026
Semantic ParsingBreaknlp18Feb 26, 2026
Graph-level classificationTWITCH E.graph18Feb 26, 2026
Graph-level classificationIMDB-Mgraph18Feb 26, 2026
Graph-level classificationIMDB-Bgraph18Feb 26, 2026
Graph-level molecular classificationNCI109graphbio medical18Feb 26, 2026
Graph-level molecular classificationNCI1graphbio medical18Feb 26, 2026
Graph-level molecular classificationBACEgraphbio medical18Feb 26, 2026
Graph-level molecular classificationBBBPgraphbio medical18Feb 26, 2026
Object DetectionBDD100K Cs→B adaptation (test)computer vision18Feb 26, 2026
Entity ClassificationRELBENCH rel-stack user-badge (test)nlp18May 18, 2026
Real-world Multimodal InteractionRealWorldQA (test)multimodalcomputer vision+118Feb 26, 2026
Document UnderstandingInfoVQA (test)computer visionnlp18Feb 26, 2026
Mathematical ReasoningMWPBENCH (out-of-domain)llm chat instructionnlp18Feb 26, 2026
Text Quality EvaluationGeneral Capability Promptsnlp18Feb 26, 2026
Facial Landmark DetectionCHARLOTTE High 1.0computer vision18Feb 26, 2026
Japanese example suggestionJLPT Total (All difficulty levels)nlp18Feb 26, 2026
Japanese example suggestionJLPT N3nlp18Feb 26, 2026
Japanese example suggestionJLPT N1nlp18Feb 26, 2026
Jailbreak AttackMultimodal Jailbreak Dataset Multi-Image (test)adversarial safety security18Feb 26, 2026