Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1198 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Emotional Talking Head Generation | MEAD Cross-ID | 24 | Apr 23, 2026 | ||
| Bash Command Execution | InterCode Bash | 24 | Jun 17, 2026 | ||
| Adversarial | LoCoMo | 24 | Apr 23, 2026 | ||
| Quadratic Assignment Problem | Taixxeyy | 24 | Apr 23, 2026 | ||
| Visual cortex alignment | Natural Scenes Dataset (NSD) (20% val) | 24 | Apr 23, 2026 | ||
| Visual Reasoning | MMMU-Pro | 24 | Apr 23, 2026 | ||
| Visual Reasoning | VizWiz | 24 | Apr 23, 2026 | ||
| Brain Tumor Segmentation | BraTS 2021 | 24 | Jun 23, 2026 | ||
| Mathematical Reasoning | MATH 4-shot | 24 | Jun 4, 2026 | ||
| Employee Morale Prediction | Firm posts Tmin, 5 posts threshold | 24 | Apr 23, 2026 | ||
| ROA Prediction | Firm posts dataset Tmin, 5 posts threshold | 24 | Apr 23, 2026 | ||
| Machine Translation | Ostraca §3.1 | 24 | Apr 23, 2026 | ||
| Adversarial Attack on RAG | FiQA | 24 | Apr 23, 2026 | ||
| Adversarial Attack on RAG | NQ | 24 | Apr 23, 2026 | ||
| Hybrid Reasoning | MATH_MIX (test) | 24 | Apr 23, 2026 | ||
| Hybrid Reasoning | CLUTRR (test) | 24 | Apr 23, 2026 | ||
| Hybrid Reasoning | Date (test) | 24 | Apr 23, 2026 | ||
| Hybrid Reasoning | MMLU (test) | 24 | Apr 23, 2026 | ||
| Hybrid Reasoning | AQUA (test) | 24 | Apr 23, 2026 | ||
| Autonomous Driving Reasoning | DriveLM-ADvLM | 24 | Apr 23, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Task | 24 | Apr 23, 2026 | ||
| Table Recognition | FinTabNet (test) | 24 | Jun 17, 2026 | ||
| End-to-end planning | nuScenes (open-loop) | 24 | Apr 21, 2026 | ||
| Vision-Language Multi-task Evaluation | MS COCO Unified Multi-task (test) | 24 | Apr 21, 2026 | ||
| Retrieval | OET-Disease Retrieval SNOMED-14 | 24 | Apr 21, 2026 |