List your company

Research

Benchmarks

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

309,131 benchmarksPage 1639 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Multi-bit LLM WatermarkingGemma2-9B-Base Max 256 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingGemma2-9B-Base Max 128 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingLLaMA3-8B-Base Max 256 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingLLaMA3-8B-Base Max 128 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingC4 GEMMA2-9B-BASE Max 256 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingC4 GEMMA2-9B-BASE Max 128 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingC4 LLaMA3-8B-BASE Max 256 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Multi-bit LLM WatermarkingC4 LLaMA3-8B-BASE Max 128 Tokensllm chat instructionadversarial safety security20Feb 26, 2026
Text Reconstruction from EmbeddingsPubMednlp20Feb 26, 2026
Text Reconstruction from EmbeddingsMS MARCOnlp20Feb 26, 2026
Repository ReconstructionRepoCraft (test)code developer ai20Feb 26, 2026
MMI ScoringMMIspeech audio20Feb 26, 2026
Long-form Question AnsweringNovel GraphRAG-Benchllm chat instructionnlp20Feb 26, 2026
Long-form Question AnsweringGraphRAG-Bench Medllm chat instructionnlp20Feb 26, 2026
Question Answering2WikiMultihopQAnlp20Feb 26, 2026
Question AnsweringHotpotQAnlp20Feb 26, 2026
ReasoningAIME24, AIME25, HMMT25 Averagellm chat instructionnlp20Feb 26, 2026
Adversarial and Jailbreaking Attack DetectionMaliciousInstructadversarial safety security20Feb 26, 2026
Adversarial and Jailbreaking Attack DetectionJailbreakBenchadversarial safety security20Feb 26, 2026
Adversarial and Jailbreaking Attack DetectionHarmBenchadversarial safety security20Feb 26, 2026
Adversarial and Jailbreaking Attack DetectionBeaverTailsadversarial safety security20Feb 26, 2026
Adversarial and Jailbreaking Attack DetectionAdvBenchadversarial safety security20Feb 26, 2026
Agentic PerformanceTAU2-Benchagents tool use20Apr 30, 2026
Audio UnderstandingClothoAQAspeech audio20Jun 18, 2026
Automatic Speech RecognitionWenetSpeech netspeech audio20Mar 26, 2026