List your company

Research

Benchmarks

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

309,131 benchmarksPage 2127 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Fine-tuningSQL (val)llm chat instruction16Jun 16, 2026
Fine-tuningViGGO (val)llm chat instruction16Jun 16, 2026
Fine-tuningGSM8k (val)llm chat instruction16Jun 16, 2026
Multi-turn agent interactionScienceWorldagents tool userobotics embodied ai16Jun 16, 2026
Multi-turn agent interactionALFWorld OODagents tool userobotics embodied ai16Jun 16, 2026
Multi-turn agent interactionALFWorld IIDagents tool userobotics embodied ai16Jun 16, 2026
Multimodal Scientific ReasoningFrontier Multimodal Scientific Reasoning Combined 240-question (test)multimodalnlp+116Jun 16, 2026
Multimodal Scientific ReasoningFrontier Multimodal Scientific Reasoning SFE (test)multimodalnlp+116Jun 16, 2026
Multimodal Scientific ReasoningFrontier Multimodal Scientific Reasoning SGI (test)multimodalnlp+116Jun 16, 2026
Non-convex optimizationFinite-sum optimization exact full-gradient initializationmiscellaneous16Jun 16, 2026
Safety Guardrail ClassificationCHILLGuard 1.0 (test)adversarial safety securityllm chat instruction16Jun 16, 2026
Safety ClassificationCombined Chinese Safety Datasetsadversarial safety security16Jun 16, 2026
Safety ClassificationChinese Response Datasetsadversarial safety security16Jun 16, 2026
Safety ClassificationChinese Prompt Datasetsadversarial safety security16Jun 16, 2026
Image reconstructionMSCOCOcomputer vision16Jun 16, 2026
Long-form Deep Research Report GenerationLong-form Deep Research Report Generation Benchmarksllm chat instruction16Jun 16, 2026
Multimodal long-horizon complex reasoningBrowseComp-VLmultimodalllm chat instruction16Jun 16, 2026
Multimodal long-horizon complex reasoningMM-Searchmultimodalllm chat instruction16Jun 16, 2026
Constrained NavigationMaze2D Narrowrobotics embodied ai16Jun 16, 2026
Constrained NavigationMaze2D Broadrobotics embodied ai16Jun 16, 2026
Image GenerationImageNet 256image generation editing16Jun 16, 2026
Multi-UAV Mission PlanningRandomly generated PUAV instancesrobotics embodied ai16Jun 16, 2026
Kill Switch EvaluationKILLBENCH System-Prompt Bypass Agent 1.0 (test)adversarial safety security16Jun 16, 2026
Kill Switch EvaluationKILLBENCH Text-based Agent 1.0 (test)adversarial safety security16Jun 16, 2026
Graduate-level ReasoningGPQA-Dllm chat instruction16Jun 16, 2026