List your company

Research

Benchmarks

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

309,131 benchmarksPage 728 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multimodal tool-useGTAmultimodalagents tool use33Jul 1, 2026
Psychosis detectionPSY-IAT (50 CV folds)bio medicalcomputer vision33Mar 18, 2026
ReasoningReasoning Benchmarks GSM8K, MATH-500, AIME24, AIME25, GPQA-Dllm chat instructionnlp33Mar 18, 2026
Multimodal Understanding and Question AnsweringMultimodal Benchmarks MME, OCRBench, DocVQA, RealWorldQA, VLMBlindmultimodalcomputer vision+133Mar 18, 2026
LLM InferenceLLaMA2 7Bllm chat instruction33Apr 28, 2026
Multi-discipline Multimodal ReasoningMMMUmultimodalllm chat instruction33Mar 24, 2026
Hierarchical Text ClassificationAAPDnlp33Mar 18, 2026
New View SynthesisT&T3d vision geometry33Mar 17, 2026
Object RemovalOBER (test)computer visionimage generation editing33May 13, 2026
Machine UnlearningImageNetadversarial safety security33May 15, 2026
Atomic and excitation energy predictionBeryllium NIST ASDbio medical33Mar 17, 2026
360 Image Quality AssessmentCVIQD (test)computer vision33Mar 17, 2026
360 Image Quality AssessmentJUFE (test)computer vision33Mar 17, 2026
Web Information ExtractionLIVEWEB-IE Overall 1.0 (test)nlpretrieval search rag33Mar 17, 2026
Web Information ExtractionLIVEWEB-IE Type IV 1.0 (test)nlpretrieval search rag33Mar 17, 2026
Web Information ExtractionLIVEWEB-IE Type III 1.0 (test)nlpretrieval search rag33Mar 17, 2026
Web Information ExtractionLIVEWEB-IE Type II 1.0 (test)nlpretrieval search rag33Mar 17, 2026
Web Information ExtractionLIVEWEB-IE Type I 1.0 (test)nlpretrieval search rag33Mar 17, 2026
Node ClassificationBlogCatalog 6-way Social Media (test)graph33Mar 17, 2026
Node ClassificationPhysics Co-authorship 5-way (test)graph33Mar 17, 2026
Node ClassificationComputers 10-way E-commerce (test)graph33Mar 17, 2026
Math ReasoningAIME 25llm chat instructionnlp33Mar 16, 2026
Policy Error Rate EstimationHC-MNIST (out-sample)robotics embodied ai33Mar 13, 2026
Anomaly DetectionGrid Loss D3 train 13.69% (test)tabular time series33Mar 13, 2026
Anomaly DetectionGrid Loss D2 Train 1.04% (test)tabular time series33Mar 13, 2026