WizWand is now SOTA2 Research

SOTA2 Research · benchmarks

Benchmarks

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

Benchmarks

309,131 indexed
TaskDatasetDomainTrendResultsLast Update
High-Resolution Visual PerceptionHRBench 8Kcomputer vision29Jul 2, 2026
Multi-hop Question AnsweringMuSiQue (dev)nlpretrieval search rag29Jun 23, 2026
Multimodal Information SeekingInfoSeekmultimodalretrieval search rag29Jun 5, 2026
Attribution Sensitivity AnalysisImgNet 2012 (val)computer vision29Jun 5, 2026
Fragment RetrievalWeChat (test)retrieval search rag29Jun 4, 2026
Fragment RetrievalMLDR (val)retrieval search rag29Jun 4, 2026
Room NavigationRoom Navigation Visual Appearance - VArobotics embodied ai29Jun 4, 2026
Room NavigationRoom Navigation Complex Instruction - CIrobotics embodied ai29Jun 4, 2026
Room NavigationRoom Navigation Common Sense - CSrobotics embodied ai29Jun 4, 2026
Room NavigationRoom Navigation Baserobotics embodied ai29Jun 4, 2026
Node ClassificationCora 3-shotgraph29Jun 11, 2026
Document ParsingOmniDocBench 1.6 (test)nlpcomputer vision29Jun 4, 2026
Mathematical reasoningAIME 25llm chat instructionnlp29Jun 30, 2026
Mathematical reasoningAIME 24llm chat instructionnlp29Jun 30, 2026
Novel View SynthesisNVIDIA (test)3d vision geometry29Jul 3, 2026
Document FormattingDOCFORMBENCHnlp29Jun 2, 2026
Harmful prompt detectionOpenAIadversarial safety security29Jul 8, 2026
Long-term forecastingETTm1 (test)tabular time series29Jun 11, 2026
Synthetic Network GenerationDBLPgraph29Jun 2, 2026
Synthetic Network GenerationYouTubegraph29Jun 2, 2026
Synthetic Network GenerationPolBlogsgraph29Jun 2, 2026
Image ClassificationTissueMNIST MedMNIST v2 (test)computer vision29Jun 2, 2026
Agentic SearchDeepSearchQAagents tool useretrieval search rag29Jun 23, 2026
Text-to-ImageUniGenBench Longimage generation editing29Jun 2, 2026
Text-to-ImageUniGenBench Shortimage generation editing29Jun 2, 2026