List your company

Research

Benchmarks

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

309,131 benchmarksPage 1217 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Complex Reasoningvcrbenchllm chat instructionnlp24Jun 23, 2026
Depth EstimationPano3D GibsonV23d vision geometry24Mar 31, 2026
VPD screeningOut-of-domain heterogeneous public Internet recordings (test)bio medicalspeech audio24Mar 19, 2026
VPD screeningIn-domain Clinical Recordings Standardized (held-out)bio medicalspeech audio24Mar 19, 2026
Jailbreak DefenseHADESadversarial safety security24Mar 19, 2026
Safety Refusal EvaluationAlpaca & StrongReject benign & harmfuladversarial safety securityllm chat instruction24Mar 19, 2026
Machine UnlearningTOFU 1.0 (Forget05)adversarial safety security24Jun 29, 2026
Machine UnlearningTOFU Forget10 Phi-1.5B modeladversarial safety security24Apr 14, 2026
Machine UnlearningTOFU Forget01 Phi-1.5B model (1%)adversarial safety security24Mar 19, 2026
Visual Question AnsweringOK-VQAmultimodalcomputer vision+124Mar 18, 2026
Image ClassificationFlowerscomputer vision24Mar 18, 2026
Image ClassificationCUBcomputer vision24Mar 18, 2026
Object Hallucination MitigationCOCO 2014computer vision24Mar 18, 2026
General IntelligenceAGI Evalllm chat instruction24Mar 18, 2026
text-to-SQLBiomedSQL (test)nlpcode developer ai24Mar 18, 2026
Factual Knowledge EvaluationDyKnow 130 time-sensitive facts Wikidata-derivedllm chat instructionnlp24Mar 18, 2026
Output ConsistencySubject and Property Perturbationsllm chat instruction24Mar 18, 2026
ClassificationIonospherecomputer visionnlp+324Mar 18, 2026
Binary ClassificationCalifornia 1%tabular time series24Mar 18, 2026
Binary ClassificationPhoneme 1%tabular time series24Mar 18, 2026
Binary ClassificationAbalone 1%tabular time series24Mar 18, 2026
Node Classificationogbn-productsgraph24May 20, 2026
Node ClassificationOgbn-arxiv naturally imbalanced setting (ρ ≈ 775.4) (test)graph24Mar 18, 2026
Robot Hand ManipulationAdroit Door medium hard v0robotics embodied ai24Mar 18, 2026
Robot Hand ManipulationAdroit Pen medium, hard v0robotics embodied ai24Mar 18, 2026