List your company

Research

Benchmarks

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

309,131 benchmarksPage 1724 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
User Simulator Goal Alignmentτ-Bench Retail (test)agents tool usellm chat instruction19May 14, 2026
LocomotionWalker2d Medium-Expert v2robotics embodied ai19May 15, 2026
LocomotionWalker2d Medium-Replay v2robotics embodied ai19May 15, 2026
LocomotionWalker2d Medium v2robotics embodied ai19May 15, 2026
LocomotionHalfCheetah Medium-Expert v2robotics embodied ai19May 15, 2026
LocomotionHalfCheetah Medium v2robotics embodied ai19May 15, 2026
General AI Assistant ReasoningBrowseComp-zh (BC-zh)llm chat instructionnlp19Mar 10, 2026
Protein Sequence DesignRFDiffusion de novo backbonesbio medical19Apr 21, 2026
Task FulfillmentMCPBenchllm chat instruction19Mar 10, 2026
Backdoor AttackImageNet 100adversarial safety security19May 20, 2026
Classificationm-pv4ger (test)computer visionnlp+319Jun 23, 2026
Video GroundingCharadesSTAcomputer visionmultimodal19Apr 10, 2026
ClassificationTEPcomputer visionnlp+319Mar 10, 2026
Inertial OdometryDiTer++ PARK (Unseen)robotics embodied ai3d vision geometry19Mar 9, 2026
Inertial OdometryDiTer++ LAWN Unseenrobotics embodied ai3d vision geometry19Mar 9, 2026
Inertial OdometryDiTer++ Forest (Seen)robotics embodied ai3d vision geometry19Mar 9, 2026
Inertial OdometryBotanic Garden 1008-03 (Unseen)robotics embodied ai3d vision geometry19Mar 9, 2026
Inertial OdometryBotanic Garden 1006-01 (Unseen)robotics embodied ai3d vision geometry19Mar 9, 2026
Inertial OdometryBotanic Garden 1005-01 (Seen)robotics embodied ai3d vision geometry19Mar 9, 2026
Emotional Intelligence evaluationEQ-Benchllm chat instruction19May 8, 2026
Emotion assessmentEmoBenchnlp19Jun 2, 2026
Document and Chart UnderstandingChartQAcomputer visionnlp19Apr 21, 2026
Video Question AnsweringVideoMMEmultimodalcomputer vision19Apr 24, 2026
Virtual Try-OnDressCodeimage generation editingcomputer vision19Mar 23, 2026
Gait RecognitionSUSTech1K 1.0 (test)computer vision19Mar 9, 2026