Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 773 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Generation | VisRAG Clean | 32 | Mar 6, 2026 | ||
| Visually Grounded Reasoning | V* Bench | 32 | Mar 10, 2026 | ||
| AI-generated image detection | UniversalFakeDetect | 32 | Apr 7, 2026 | ||
| Scientific Code Generation | ScienceAgentBench (test) | 32 | Jun 19, 2026 | ||
| Geometry | MathVista mini | 32 | Mar 4, 2026 | ||
| Image Classification | CIFAR-10 | 32 | Mar 4, 2026 | ||
| Multi-Turn Medical Dialogue | MedMCQA | 32 | Mar 4, 2026 | ||
| Multi-Turn Medical Dialogue | MedQA | 32 | Mar 4, 2026 | ||
| Multi-Turn Medical Dialogue | MedicalExam | 32 | Mar 4, 2026 | ||
| Target-Aspect-Sentiment Detection | FlightABSA | 32 | May 28, 2026 | ||
| Image Captioning | DOCCI 500 (test) | 32 | Mar 4, 2026 | ||
| Image Classification | Generic Image Dataset 224x224 | 32 | Mar 4, 2026 | ||
| Text-to-image generation | Image Reward (Calibration) | 32 | Mar 4, 2026 | ||
| Cross Reenactment | HDTF | 32 | Jun 16, 2026 | ||
| Graph Reasoning | GRBENCH Legal | 32 | Mar 4, 2026 | ||
| Graph Reasoning | GRBENCH E-Commerce | 32 | Mar 4, 2026 | ||
| Graph Reasoning | GRBENCH Academic | 32 | Mar 4, 2026 | ||
| Graph Reasoning | GRBENCH Literature | 32 | Mar 4, 2026 | ||
| Graph Reasoning | GRBENCH Healthcare | 32 | Mar 4, 2026 | ||
| Program Synthesis | HumanEval | 32 | Mar 10, 2026 | ||
| Multi-hop QA Retrieval | 2Wiki | 32 | Jun 16, 2026 | ||
| Multi-task Image Classification | 8 Vision Tasks Low Confidence setting (test) | 32 | Mar 4, 2026 | ||
| Multi-task Image Classification | 8 Vision Tasks Norm Mismatch setting (test) | 32 | Mar 4, 2026 | ||
| Mathematical Reasoning | GSM8K OOD (test) | 32 | Mar 4, 2026 | ||
| Commonsense Reasoning | CSQA OOD (test) | 32 | Mar 4, 2026 |