Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1811 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Game Interaction | MMG2Skill-Bench Game | 18 | Jun 2, 2026 | ||
| GUI Navigation | MMG2Skill-Bench GUI | 18 | Jun 2, 2026 | ||
| Part Pose Estimation | HOI4D synthetic (test) | 18 | Jun 2, 2026 | ||
| Spatial Reasoning | Controlled Synthetic - CS | 18 | Jun 2, 2026 | ||
| API Use | API-Bank | 18 | Jun 2, 2026 | ||
| Search-based Question Answering | SearchQA | 18 | Jun 2, 2026 | ||
| Tool Use | ToolHop | 18 | Jun 2, 2026 | ||
| Knowledge & Instruction Following | GPQA Diamond | 18 | Jun 2, 2026 | ||
| Neuromorphic Event Classification | ASL-DVS | 18 | Jun 4, 2026 | ||
| Code runtime regression | CodeNet (test) | 18 | Jun 2, 2026 | ||
| Overall Performance Evaluation | Consolidated Evaluation Benchmark | 18 | Jun 2, 2026 | ||
| Preference Aggregation | Preference Evaluation Suite Aggregate | 18 | Jun 2, 2026 | ||
| General Language Capability Evaluation | General Capability Suite Aggregate | 18 | Jun 2, 2026 | ||
| Methane Plume Detection | STARCOP (test) | 18 | Jun 2, 2026 | ||
| Certified Robustness | CIFAR10 | 18 | Jun 2, 2026 | ||
| Link-property prediction | tgbl-review v2 (test) | 18 | Jun 11, 2026 | ||
| Legal Reasoning | LegalBench | 18 | Jun 2, 2026 | ||
| Logical Reasoning | BBH Web of Lies | 18 | Jun 2, 2026 | ||
| Question Answering | BBH Disambiguation QA | 18 | Jun 2, 2026 | ||
| Natural Language Understanding | GLUE8 (val) | 18 | Jun 2, 2026 | ||
| Biomedical Multimodal Reasoning | LAB-Bench | 18 | Jun 4, 2026 | ||
| Object Detection | PASCAL VOC 2007 (test) | 18 | Jun 2, 2026 | ||
| Object Detection | MS COCO 20% subset (test) | 18 | Jun 2, 2026 | ||
| Volumetric Segmentation | LUNA16 -> C19-CT (test) | 18 | Jun 2, 2026 | ||
| Abnormality Classification | CT-Rate AHPH-10K (test) | 18 | Jun 2, 2026 |