Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 109 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Language Modeling | PG-19 (test) | 112 | May 19, 2026 | ||
| Optical Flow | Sintel Final (train) | 112 | May 11, 2026 | ||
| Object Recognition | PACS (leave-one-domain-out) | 112 | Feb 26, 2026 | ||
| Multi-view 3D Reconstruction | ModelNet40 (test) | 112 | Feb 26, 2026 | ||
| Domain Generalization | TerraInc | 112 | Jul 3, 2026 | ||
| Multimodal Understanding | MMMU (test) | 112 | Jul 7, 2026 | ||
| Rescheduling | GDB Failure Scenarios | 111 | Jun 1, 2026 | ||
| Prediction-grounded correlation with accuracy difference | ImageNet 100 | 111 | May 18, 2026 | ||
| Science Question Answering | ARC Challenge | 111 | Jun 12, 2026 | ||
| Lipschitz constant estimation | Large-scale Neural Networks | 111 | Apr 9, 2026 | ||
| Medical Question Answering | MMLU Med | 111 | Jun 25, 2026 | ||
| Constrained Multi-objective Optimization | MW | 111 | Jun 30, 2026 | ||
| Temporal Grounding | ActivityNet | 111 | Jun 24, 2026 | ||
| Reasoning | GSM8K | 111 | Jun 30, 2026 | ||
| Single-hop Question Answering | LoCoMo | 111 | May 26, 2026 | ||
| Open-domain Question Answering | LoCoMo | 111 | May 26, 2026 | ||
| Mathematical Reasoning | MATH500 (full) | 111 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | DCI | 111 | Jul 2, 2026 | ||
| Multimodal Benchmark | MMBench (MMB) | 111 | Jun 24, 2026 | ||
| Multivariate time series prediction | PEMS03 | 111 | Feb 26, 2026 | ||
| Medical Image Classification | BTC | 111 | May 7, 2026 | ||
| Code Generation | APPS | 111 | May 18, 2026 | ||
| Video Super-Resolution | UDM10 | 111 | Jun 12, 2026 | ||
| Image Captioning | Flickr30K | 111 | Feb 26, 2026 | ||
| Spatio-temporal forecasting | PEMS08 (test) | 111 | Jun 12, 2026 |