List your company

Research

Benchmarks

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

309,131 benchmarksPage 2283 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multi-hop Question AnsweringHotpotQA 800 documentsnlpretrieval search rag16Feb 26, 2026
Multi-hop Question AnsweringHotpotQA 400 documentsnlpretrieval search rag16Feb 26, 2026
Question AnsweringAverage (PopQA, HotpotQA, 2Wiki, MuSiQue, Bamboogle)nlp16Jul 9, 2026
End-to-end Tool-useToolBench I1 v1agents tool use16Feb 26, 2026
ReasoningAIME 25llm chat instructionnlp16Apr 23, 2026
Mathematical ReasoningOlympiadBench (OLY.)llm chat instructionnlp16Feb 26, 2026
HallucinationHallusionBenchimage generation editing16Feb 26, 2026
Interactive Agent TaskTRIP-Bench Overallagents tool userobotics embodied ai16Feb 26, 2026
Interactive Agent TaskTRIP-Bench Hard PMRagents tool userobotics embodied ai16Feb 26, 2026
Interactive Agent TaskTRIP-Bench (Hard FIT)agents tool userobotics embodied ai16Feb 26, 2026
Interactive Agent TaskTRIP-Bench Midagents tool userobotics embodied ai16Feb 26, 2026
Interactive Agent TaskTRIP-Bench Easyagents tool userobotics embodied ai16Feb 26, 2026
Deep searchhleretrieval search ragagents tool use16Jul 1, 2026
RegressionParkinsonstabular time series16Feb 26, 2026
GUI AgentAC Highagents tool use16Feb 26, 2026
GUI AgentAC Lowagents tool use16Feb 26, 2026
Reward ModelingMMRB 2llm chat instruction16Jun 26, 2026
Mathematical ReasoningVerify-RL (D5)llm chat instructionnlp16Feb 26, 2026
Concept UnlearningMMA-Diffusioncomputer visionnlp16Feb 26, 2026
Medical LLM EvaluationLLMEval Medbio medicalllm chat instruction16Mar 23, 2026
Medical Question AnsweringHealthBench Overallbio medicalnlp16Feb 26, 2026
Open-ended text generationLaw-MT Out of Domain (test)nlp16Feb 26, 2026
Instruction FollowingIFEvalllm chat instruction16Apr 3, 2026
Length PredictionForeLen Avg. 1.0 (test)nlp16Feb 26, 2026
Length PredictionForeLen RL 1.0 (test)nlp16Feb 26, 2026