List your company

Research

Benchmarks

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

309,131 benchmarksPage 541 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Textual ExplanationImageNet-1K misclassified casesnlp40May 19, 2026
Watermark RemovalMS-COCOimage generation editing40May 20, 2026
Goal-conditioned visual planningCrossTask T=4 88 (test)robotics embodied aicomputer vision40May 19, 2026
Image ClassificationCIFAR-10 (test)computer vision40May 19, 2026
Multimodal UnderstandingVLM Evaluation Suite Hall, MME, AI2D, RWQA, SQA, POPE, MBen, MBzh, CCB, VSR, V7Wmultimodal40May 19, 2026
Referring Expression CountingREC 8K (test)computer visionnlp40Jun 24, 2026
Cyber Defense Mean ReturnCybORG CAGE-2 Post-Session Evaluation (test)adversarial safety security40May 18, 2026
Agent Return VolatilityCAGE-2 v1 (test)agents tool use40May 18, 2026
Zero-shot Gene Inhibitor Prediction10 canonical genes inhibitor libraries (Unseen gene knockout)bio medical40May 18, 2026
3D Segmentation (Enhancing Tumor)BraTS 183d vision geometrybio medical+140May 15, 2026
Causal ReasoningBBH Causal Judgementnlp40Jun 2, 2026
Hallucination detectionSQuADllm chat instructionnlp40May 15, 2026
Next-event predictionTaobaotabular time series40Jun 9, 2026
ClusteringCENSUS 1990 (full)tabular time series40May 14, 2026
Copyright VerificationSVHN (test)computer vision40May 14, 2026
Copyright VerificationFashionMNIST (test)computer vision40May 14, 2026
Information RetrievalBANKING77retrieval search rag40May 13, 2026
Information RetrievalNFCORPUSretrieval search rag40May 13, 2026
Information RetrievalARGKP 21retrieval search rag40May 13, 2026
Object Hallucination DetectionObjects365computer visionmultimodal40May 13, 2026
Long-term conversational memoryLongMemEval Smallllm chat instruction40Jun 4, 2026
Novel View SynthesisDL3DV3d vision geometry40May 13, 2026
Credit Card Fraud DetectionBankSim (test)tabular time series40May 13, 2026
Fraud DetectionBankSimtabular time series40May 13, 2026
Credit Card Fraud DetectionBankSimtabular time series40May 13, 2026