List your company

Research

Benchmarks

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

309,131 benchmarksPage 2063 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Commonsense ReasoningWNG-Lnlp17Feb 26, 2026
Question AnsweringSteuerEx 1.0 (n=115)nlp17Feb 26, 2026
ReasoningLanguage Task Suite (COPA, HS, LB, OBQA, PIQA, Race, SciQ, ARC, SIQA, WG) zero-shot standardllm chat instructionnlp17Feb 26, 2026
Language ModelingOpenWebText standard (test)nlp17Feb 26, 2026
Question AnsweringDetectiveQAnlp17Jun 23, 2026
Logical Reasoning Question AnsweringLSATnlpllm chat instruction17Apr 28, 2026
General Capability EstimationGeneral Capability Estimation Framework 1.0llm chat instruction17Feb 26, 2026
Multi-hop Question Answering2WikiMultiHopQA (2WikiMQA) (official evaluation)nlpretrieval search rag17Feb 26, 2026
Multi-hop Question AnsweringHotpotQA (official evaluation)nlpretrieval search rag17Feb 26, 2026
Tool-based Question AnsweringToolQA hardagents tool useretrieval search rag17Feb 26, 2026
Tool-use Question AnsweringToolQA Easy 1.0agents tool useretrieval search rag17Feb 26, 2026
Molecular dockingbrafbio medical17Feb 26, 2026
Video SummarizationTVSum single ground truth (test)computer visionnlp17Feb 26, 2026
Video SummarizationSumMe single ground truth (test)computer visionnlp17Feb 26, 2026
Evaluation of metrics' alignment with human judgmentRadEvalXnlp17Jun 16, 2026
Visual ReasoningVSPmultimodalcomputer vision17Jun 2, 2026
Online Bin Packing ProblemWeibull BPP 10k 500miscellaneous17Feb 26, 2026
Online Bin Packing ProblemWeibull BPP 10k 100miscellaneous17Feb 26, 2026
Multimodal Mathematical ReasoningGEOQA-8k (test)multimodalnlp+117May 28, 2026
Mathematical ReasoningOlympiadllm chat instructionnlp17Feb 26, 2026
Cybersecurity EvaluationSecBenchadversarial safety security17Feb 26, 2026
Cybersecurity Knowledge EvaluationMMLU Securityadversarial safety securitynlp17Feb 26, 2026
Vulnerability PredictionCWE-Predictionadversarial safety securitycode developer ai17Feb 26, 2026
Cyber Threat Intelligence ReasoningCTI-Reasoningnlp17Feb 26, 2026
Attack Technique ExtractionCTIBench ATEadversarial safety securitynlp17Feb 26, 2026