List your company

Research

Benchmarks

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

309,131 benchmarksPage 841 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Long-tailed Image ClassificationTinyImageNet long-tailed (test)computer vision30May 14, 2026
Long-tailed Image ClassificationCIFAR100 long-tailed (test)computer vision30May 14, 2026
PruningMNISTmiscellaneous30May 14, 2026
Language UnderstandingMMLUnlp30May 14, 2026
Graph ReasoningOOD graph (test)graph30May 14, 2026
ReasoningIn-distribution reasoning (test)llm chat instructionnlp30May 14, 2026
Time Series ForecastingWeather 5% train data (test)tabular time series30May 14, 2026
Time Series ForecastingElectricity (5% train)tabular time series30May 14, 2026
Long-form GenerationAlpacallm chat instructionnlp30May 14, 2026
Backdoor DefenseLLM Backdoor Defense (test)adversarial safety security30May 14, 2026
Phenotype MiningBiolarkGSC+bio medical30May 14, 2026
Multimodal ReasoningSLAKEmultimodalnlp30Jul 1, 2026
Open-domain QAOverall QA Suite (NQ, TriviaQA, PopQA, HotpotQA, 2WikiMultiHopQA, MuSiQue, Bamboogle)retrieval search ragnlp30May 13, 2026
Open-domain Single-hop QATriviaQAretrieval search ragnlp30May 13, 2026
PDE IdentificationAdv-Diff PDEmiscellaneous30May 13, 2026
Mathematical ReasoningCombined Mathematical Reasoning Benchmarksllm chat instructionnlp30May 19, 2026
General AI Assistant TasksGAIAllm chat instructionagents tool use+330May 13, 2026
Shopping PlanningShopping Planningagents tool usellm chat instruction30May 13, 2026
Travel PlanningTravel Planningllm chat instruction30May 13, 2026
Binding affinity predictionSKEMPI v2.0bio medical30May 13, 2026
Malicious Training Sample DetectionAttack Training Samples (test)adversarial safety security30May 13, 2026
Bus Routing ProblemBRPmiscellaneous30May 12, 2026
Location Routing ProblemLRPmiscellaneous30May 12, 2026
Traveling Salesman ProblemTSPmiscellaneous30May 12, 2026
Deepfake DetectionFaceSwapper (test)computer visionadversarial safety security30May 12, 2026