List your company

Research

Benchmarks

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

309,131 benchmarksPage 1008 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Long-context reasoningOOL-Pairsllm chat instruction27Mar 23, 2026
Long-context reasoningOOLONGllm chat instruction27Mar 23, 2026
Long-context retrievalS-NIAHretrieval search ragllm chat instruction27Mar 23, 2026
Coding Question AnsweringCodeQAcode developer ai27Mar 23, 2026
Long-context reasoning (Pairs)OOL-Pairsllm chat instruction27Mar 23, 2026
Semantic Needle-In-A-HaystackS-NIAHretrieval search rag27Mar 23, 2026
Yes/No Question AnsweringQuilt-VQAnlp27Mar 23, 2026
Node ClassificationWikiCSgraph27May 13, 2026
Multiple-choice Question AnsweringMMLU zero-shot (test)nlp27May 25, 2026
Multimodal ReasoningMMMUmultimodalnlp27May 28, 2026
Mathematical ReasoningHMMT Feb25llm chat instructionnlp27May 11, 2026
Visual Agentic ReasoningSokobanagents tool usecomputer vision+127May 6, 2026
Spatio-temporal reasoningV-STAR (test)computer visionnlp27Jun 24, 2026
Few-shot Action RecognitionHMDB51 5-shotcomputer vision27Mar 20, 2026
Few-shot Action RecognitionUCF101 5-shotcomputer vision27Mar 20, 2026
Few-shot Action RecognitionKinetics 5-shotcomputer vision27Mar 20, 2026
Information RetrievalDBPedia-Entity BEIRretrieval search rag27Jun 11, 2026
Information RetrievalTREC-COVID BEIRretrieval search rag27Jun 11, 2026
Bus holding controlSimulated bidirectional bus corridor sigma_test = 2.0 1.0 (test)robotics embodied ai27Mar 20, 2026
Bus holding controlSimulated bidirectional bus corridor sigma_test = 1.5 1.0 (test)robotics embodied ai27Mar 20, 2026
Bus holding controlSimulated bidirectional bus corridor sigma 1.0 (test)robotics embodied ai27Mar 20, 2026
Backdoor DefenseShort Prompt Datasetadversarial safety security27Mar 19, 2026
Science ReasoningGPQAnlpbio medical27Apr 16, 2026
Visual GroundingVIEW2SPACE v1multimodalcomputer vision27Mar 18, 2026
Visual CountingVIEW2SPACE v1computer vision27Mar 18, 2026