List your company

Research

Benchmarks

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

309,131 benchmarksPage 1491 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
LLM InferenceMBPPllm chat instruction21Feb 26, 2026
LLM InferenceMath500llm chat instruction21Feb 26, 2026
LLM InferenceLiveCodeBenchllm chat instruction21Feb 26, 2026
Language UnderstandingMMLU o=1 (Semantic-level)nlp21Feb 26, 2026
Question AnsweringTruthfulQA o=1 Domain-level splitnlp21Feb 26, 2026
Question AnsweringTruthfulQA o=1 Semantic-levelnlp21Feb 26, 2026
Question AnsweringTruthfulQA o=1 (Exact split)nlp21Feb 26, 2026
Multitask Language UnderstandingMMLU Semantic-level split, o=3nlpllm chat instruction21Feb 26, 2026
Question AnsweringTruthfulQA Domain-level split, o=3nlp21Feb 26, 2026
Question AnsweringTruthfulQA Semantic-level split o=3nlp21Feb 26, 2026
Question AnsweringTruthfulQA Exact split, o=3nlp21Feb 26, 2026
Automatic Speech RecognitionLibriSpeech (LS) cleanspeech audio21Jun 11, 2026
Automatic Speech RecognitionWenetSpeech Chuan hardspeech audio21Apr 21, 2026
Automatic Speech RecognitionWenetSpeech Chuan easyspeech audio21Apr 21, 2026
Document RetrievalBEIR 15retrieval search rag21Feb 26, 2026
Code generationHEvalcode developer ai21Jun 17, 2026
General Task PerformanceMacro-average (Mathematics, Multi-Hop QA, Code Generation)nlpcode developer ai+121Feb 26, 2026
Code GenerationCode Generationcode developer ai21Feb 26, 2026
Hallucination evaluationMMLU-Pro Law (test)llm chat instructionnlp21Feb 26, 2026
Jailbreak DefenseJailbreakBench and AdvBenchadversarial safety security21Feb 26, 2026
Scientific ReasoningGPQA Diamondnlp21Feb 26, 2026
Code Question AnsweringPython Code Question Answering downstreamcode developer ainlp21Feb 26, 2026
Code CompletionPython Code Completion downstreamcode developer ai21Feb 26, 2026
Knowledge EditingEVK-Benchnlpllm chat instruction21Feb 26, 2026
Optimization ModelingComplexORmiscellaneous21May 29, 2026