List your company

Research

Benchmarks

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

309,131 benchmarksPage 578 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Expert-level Question AnsweringGPQA Diamondllm chat instructionnlp39Jun 1, 2026
Reading ComprehensionBelebelenlpReading Comprehension on Belebele (34 Languages) performance trend39Mar 10, 2026
Code GenerationHumanEval OODcode developer ai39May 15, 2026
Visual document retrievalViDoRe V2retrieval search ragcomputer vision+139Jun 1, 2026
Automatic Speech RecognitionLS Cleanspeech audio39Jun 9, 2026
Text-to-speechSeed-TTS (eval)speech audio39Feb 26, 2026
Mathematical ReasoningHMMT Nov 2025llm chat instructionnlp39Jul 9, 2026
Long-context language understandingRULER 32k context lengthllm chat instructionnlp39May 13, 2026
Machine TranslationFLORES-200 (devtest)nlp39May 28, 2026
Transferable Adversarial AttackAdvBench LLM Classifier (test)adversarial safety security39Feb 26, 2026
Machine-Generated Text DetectionEssay (test)nlp39May 18, 2026
Open ended generationTruthfulQA Without Rejected Samples open-ended (full)llm chat instruction39Feb 26, 2026
Open ended generationTruthfulQA With All Samples open-ended (full)llm chat instruction39Feb 26, 2026
Automated Software EngineeringSWE-bench Verifiedcode developer ai39Feb 26, 2026
Mathematical ReasoningGSM8K (test)llm chat instructionnlp39Feb 26, 2026
Visual Retrieval-Augmented GenerationVisual-RAGretrieval search ragmultimodal+139May 14, 2026
Mathematical ReasoningAIME 24llm chat instructionnlp39Feb 26, 2026
NERMalayalam NER (test)nlp39Feb 26, 2026
Sentiment ClassificationBangla (test)nlp39Feb 26, 2026
Mathematical ReasoningOlympiadBenchllm chat instructionnlp39Feb 26, 2026
Conditional Shapley value estimationAbalone M=8 (all)tabular time series39Feb 26, 2026
Safety evaluationUnsafeBenchadversarial safety security39Jul 2, 2026
Medical Visual Question AnsweringMMMU Health & Medicine (test)multimodalbio medical39Apr 14, 2026
Text ClusteringDBp Fnlp39Feb 26, 2026
Conformal Prediction15 datasets (average)tabular time series39May 25, 2026