Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1846 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Polyp Segmentation | Kvasir-Seg Domain B (test) | 18 | Apr 21, 2026 | ||
| Polyp Segmentation | CVC-ClinicDB Domain A (test) | 18 | Apr 21, 2026 | ||
| Machine Unlearning | TOFU | 18 | Apr 21, 2026 | ||
| Science Question Answering | ScienceQA Image | 18 | Jun 18, 2026 | ||
| Deepfake Detection | Deepfake Detection Challenge Preview (DFDCP) | 18 | Apr 21, 2026 | ||
| Uncertainty Attribution | UA-Bench Reasoning-intensive Tasks | 18 | Apr 21, 2026 | ||
| Uncertainty Attribution | UA-Bench Knowledge-intensive Tasks | 18 | Apr 21, 2026 | ||
| Embodied Agent Task | ScienceWorld Unseen | 18 | Apr 21, 2026 | ||
| Embodied Agent Task | ScienceWorld Seen | 18 | Apr 21, 2026 | ||
| Embodied Agent Task | VirtualHome Unseen | 18 | Apr 21, 2026 | ||
| Embodied Agent Task | ALFWorld Seen | 18 | Apr 21, 2026 | ||
| Text-based Task Completion | Jericho | 18 | Apr 21, 2026 | ||
| Text-based Task Completion | ScienceWorld | 18 | Apr 21, 2026 | ||
| Text-based Task Completion | AlfWorld | 18 | Apr 21, 2026 | ||
| Text-based Task Completion | TW Express | 18 | Apr 21, 2026 | ||
| Text-based Task Completion | TextWorld | 18 | Apr 21, 2026 | ||
| Intervention | CogBiasESC (test) | 18 | Apr 21, 2026 | ||
| Cognitive Distortion Diagnose | CogBiasESC (test) | 18 | Apr 21, 2026 | ||
| Inference Efficiency | General LLM Prompts | 18 | Apr 21, 2026 | ||
| Malicious Query Safety Evaluation | JailBench | 18 | Apr 21, 2026 | ||
| Malicious Query Safety Evaluation | AdvBench | 18 | Apr 21, 2026 | ||
| Streaming Video Understanding | StreamBench | 18 | Jun 19, 2026 | ||
| Path Planning | Synthetic | 18 | Apr 21, 2026 | ||
| Path Planning | PASTIS | 18 | Apr 21, 2026 | ||
| Climate Discovery | ClimaBench 2025 | 18 | Apr 21, 2026 |