Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 348 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Commonsense Reasoning | COPA (test) | 54 | Jun 1, 2026 | ||
| Object Hallucination Evaluation | POPE | 53 | Jul 1, 2026 | ||
| Oriented Object Detection | DOTA v1.0 | 53 | Jun 5, 2026 | ||
| Node Classification | shape (test) | 53 | Jun 4, 2026 | ||
| Node Classification | grid (test) | 53 | Jun 4, 2026 | ||
| Node Classification | cycle (test) | 53 | Jun 4, 2026 | ||
| Node Classification | community (test) | 53 | Jun 4, 2026 | ||
| Classification | 11 biomedical datasets (test) | 53 | Jun 4, 2026 | ||
| Inductive Dynamic Link Prediction | LastFM | 53 | Jul 7, 2026 | ||
| Zero-shot Reasoning | ARC Challenge | 53 | Jun 4, 2026 | ||
| Language Modeling | Lambada, C4, WikiText2 Aggregate | 53 | Jun 2, 2026 | ||
| Image Classification | EuroSAT | 53 | Jun 23, 2026 | ||
| Image Classification | 8 vision tasks Average | 53 | May 25, 2026 | ||
| Commonsense Reasoning | HellaSwag | 53 | Jun 1, 2026 | ||
| Weakly Supervised Object Localization | ILSVRC | 53 | Jul 1, 2026 | ||
| Reasoning | BBH | 53 | Jun 4, 2026 | ||
| Embodied AI | EmbodiedBench EB-Habitat | 53 | May 11, 2026 | ||
| Simulation-based Inference | Hierarchical SIR | 53 | Apr 23, 2026 | ||
| Ultrasound Image Segmentation | BUSI | 53 | Jul 9, 2026 | ||
| Software Engineering | SWE-bench Verified | 53 | Jun 17, 2026 | ||
| Mathematical Reasoning | Math Benchmarks GSM8K, Minerva, MATH, MathQA | 53 | Apr 14, 2026 | ||
| Multimodal Chain-of-Thought Reasoning | M3CoT | 53 | Jun 9, 2026 | ||
| Multistep Reasoning | MuSR | 53 | May 29, 2026 | ||
| Sequential Recommendation | Beauty | 53 | Jun 18, 2026 | ||
| Code Correctness Evaluation | APPS | 53 | May 28, 2026 |