Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1448 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Conversational Question Answering | MMCoQA | 21 | May 7, 2026 | ||
| Multimodal Perception | BLINK | 21 | May 7, 2026 | ||
| Commonsense Reasoning | Physical IQA (PIQA) | 21 | May 6, 2026 | ||
| Survival Analysis | METABRIC | 21 | Jun 4, 2026 | ||
| Classification | 150 dataset-fold combinations | 21 | May 6, 2026 | ||
| Safeguarding LLM Agents against prompt injection | Banking and Slack (test) | 21 | May 6, 2026 | ||
| Agitation score prediction | Bridge2AI (speaker-independent CV) | 21 | May 6, 2026 | ||
| General-purpose Language Evaluation | SCAN | 21 | May 4, 2026 | ||
| Affordance Grounding | ReasonAff (test) | 21 | May 4, 2026 | ||
| Distributed Training | LLaMA2 13B | 21 | May 4, 2026 | ||
| Safety Classification | HoliSafe-Bench | 21 | May 4, 2026 | ||
| Safety Classification | UnsafeBench | 21 | May 4, 2026 | ||
| Derivative recovery | sinusoidal p=0.25 (test) | 21 | May 4, 2026 | ||
| Wafer Defect Analysis | Wafer Defect Analysis | 21 | May 1, 2026 | ||
| Wafer map analysis | Wafer map analysis dataset | 21 | May 1, 2026 | ||
| Mathematical Reasoning | GSM8K | 21 | Apr 30, 2026 | ||
| PointButton2 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| PointButton1 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| PointPush2 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| PointPush1 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| PointGoal2 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| PointGoal1 | Safety-Gymnasium | 21 | Apr 30, 2026 | ||
| Attribute Value Extraction | Amazon Reviews 2023 | 21 | Apr 30, 2026 | ||
| Compositional Reasoning | WebAggregatorQA | 21 | Apr 30, 2026 | ||
| Classification | Higgs (train) | 21 | Apr 30, 2026 |