List your company

Research

Benchmarks

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

309,131 benchmarksPage 2401 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Chat qualityMT-Bench ShareGPTllm chat instruction15May 13, 2026
Knowledge generalizationMMLU OpenOrcallm chat instruction15May 13, 2026
Knowledge generalizationMMLU Wizardllm chat instruction15May 13, 2026
Instruction complianceIFEval Alpacallm chat instruction15May 13, 2026
Instruction complianceIFEval Dolly-15Kllm chat instruction15May 13, 2026
Incremental LearningTiny-ImageNet 5 taskcomputer visiontabular time series15May 13, 2026
Model Utility EvaluationVL-Guard SSllm chat instruction15May 13, 2026
Safety EvaluationVL-Guard (U)adversarial safety security15May 13, 2026
Safety EvaluationVL-Guard SUadversarial safety security15May 13, 2026
Continuous ControlGym MuJoCo Suite Aggregaterobotics embodied ai15May 13, 2026
Continuous ControlGym MuJoCo Humanoid v4robotics embodied ai15May 13, 2026
Continuous ControlGym MuJoCo Hopper v4robotics embodied ai15May 13, 2026
Machine UnlearningYearsadversarial safety security15May 13, 2026
Machine UnlearningWMDP Bioadversarial safety security15May 13, 2026
Data-to-TextBAGELnlp15May 13, 2026
Text SummarizationQAGS-Xnlp15May 13, 2026
Text SummarizationQAGS-Cnlp15May 13, 2026
Text SummarizationRank19nlp15May 13, 2026
Text SummarizationNewsroom segment-levelnlp15May 13, 2026
Text SummarizationSummEval segment-levelnlp15May 13, 2026
Text SummarizationREALSumm system-levelnlp15May 13, 2026
Novel View SynthesisWaymo3d vision geometry15May 13, 2026
Multi-image retrievalMS-COCO Randomretrieval search ragcomputer vision15May 13, 2026
Text-to-Image GenerationGenEvalimage generation editing15May 13, 2026
Multi-task Reinforcement LearningMeta-World MT10 V2robotics embodied ai15May 13, 2026