Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1135 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Health misinformation detection | HealthFC | 25 | May 19, 2026 | ||
| Procedural Graph Extraction | PAGED (test) | 25 | Feb 26, 2026 | ||
| Question Answering | 2Wiki 100K context | 25 | Apr 27, 2026 | ||
| Medical Calculation and Tool Use | MedMCP-Calc Overall | 25 | Feb 26, 2026 | ||
| Medical Calculation and Tool Use | MedMCP-Calc Special Populations & Universal Tools | 25 | Feb 26, 2026 | ||
| Medical Calculation and Tool Use | MedMCP-Calc Neurology & Psychiatry | 25 | Feb 26, 2026 | ||
| Medical Calculation and Tool Use | MedMCP-Calc Internal Medicine & Organ Systems | 25 | Feb 26, 2026 | ||
| Medical Calculation and Tool Use | MedMCP-Calc Critical Care & Perioperative Medicine | 25 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH-500 | 25 | Feb 26, 2026 | ||
| GUI Grounding | ScreenSpot v1 (test) | 25 | Feb 26, 2026 | ||
| Function Calling | BFCL v4 | 25 | May 21, 2026 | ||
| Multi-turn tool-use | AppWorld | 25 | Feb 26, 2026 | ||
| Reward Modeling | EditReward-Bench | 25 | Jun 26, 2026 | ||
| Creative Writing | Arena-Hard Creative Writing v2 | 25 | Feb 26, 2026 | ||
| 3D Scene Reconstruction | Tanks-and-Temples | 25 | Feb 26, 2026 | ||
| 3D Scene Reconstruction | NeRF-Synthetic | 25 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | Flickr30K | 25 | Feb 27, 2026 | ||
| Diabetic Retinopathy (DR) grading | APTOS | 25 | Mar 16, 2026 | ||
| Image Dehazing | RESIDE-6K (test) | 25 | Apr 23, 2026 | ||
| Math & Knowledge | MathVista mini | 25 | Feb 26, 2026 | ||
| Jailbreak | AdvBench Ensemble configuration GPT-4o | 25 | Feb 26, 2026 | ||
| Text Clustering | DBp B | 25 | Feb 26, 2026 | ||
| Text Clustering | YRev | 25 | Feb 26, 2026 | ||
| Text Clustering | SST-5 | 25 | Feb 26, 2026 | ||
| Text Clustering | SST-2 | 25 | Feb 26, 2026 |