List your company

Research

Benchmarks

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

309,131 benchmarksPage 1552 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Image ThresholdingSatellite Images (test)computer vision20May 27, 2026
Image ThresholdingNatural Images (test)computer vision20May 27, 2026
Image SegmentationMedical Images (test)computer vision20May 27, 2026
Image SegmentationSatellite Images (test)computer vision20May 27, 2026
Image SegmentationNatural Images (test)computer vision20May 27, 2026
Multi-task EvaluationAggregate (GSM8K, BFCL, Spider, HumanEval)miscellaneous20May 27, 2026
Text-to-SQLSpider no-easynlpcode developer ai20May 27, 2026
Function Calling / Tool UseBFCL parallel parallel-multiple Actionsagents tool use20May 27, 2026
Code GenerationLiveCodeBench v6code developer ai20Jul 3, 2026
Transmitter IdentificationWiSig (Day 4)speech audio20May 27, 2026
Transmitter IdentificationWiSig (Day 3)speech audio20May 27, 2026
Transmitter IdentificationWiSig (Day 2)speech audio20May 27, 2026
Solving linear elasticity equations2D elasticity systems (λ = 10, μ = 1)miscellaneous20May 27, 2026
Capacitated Vehicle Routing ProblemImplosion CVRP50miscellaneous20Jun 4, 2026
Traveling Salesman ProblemImplosion TSP100miscellaneous20Jun 4, 2026
Mathematical ReasoningMathematical Reasoning Benchmarks GSM8K, MATH500, ASDiv, SVAMP, AMC23 (test)llm chat instructionnlp20May 27, 2026
One-Time Knowledge EditingZsREnlp20May 27, 2026
One-Time EditCounterFactllm chat instruction20May 27, 2026
Image GenerationCIFAR10image generation editing20May 27, 2026
Language GenerationLM1B 1024 sequences of length 128nlp20May 27, 2026
Depth Estimation7Scenes DA3 benchmark BASE (test)3d vision geometry20May 27, 2026
Camera Pose EstimationScanNet++ DA33d vision geometrycomputer vision20May 27, 2026
Camera Pose Estimation7Scenes DA3 benchmark3d vision geometrycomputer vision20May 27, 2026
Camera Pose EstimationHiRoom DA3 benchmark3d vision geometrycomputer vision20May 27, 2026
Step AccuracyAndroidControl High Level v2agents tool use20May 27, 2026