Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 449 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Causal Estimation | Street Outreach Data | 45 | Apr 21, 2026 | ||
| Knowledge Retrieval | 2WikiMultihopQA | 45 | Apr 21, 2026 | ||
| Knowledge Retrieval | HotpotQA | 45 | Apr 21, 2026 | ||
| Knowledge Retrieval | PopQA | 45 | Apr 21, 2026 | ||
| Knowledge Retrieval | NQ | 45 | Apr 21, 2026 | ||
| Question Answering | Riddle (test) | 45 | Apr 21, 2026 | ||
| Code Generation | LCB v5 | 45 | May 19, 2026 | ||
| Personalized distractor generation | Discrete_40 Student_1361 | 45 | Apr 21, 2026 | ||
| Personalized distractor generation | Eedi 100 Student 1361 | 45 | Apr 21, 2026 | ||
| Point Cloud Classification | ModelNet40 | 45 | Apr 20, 2026 | ||
| Point Cloud Classification | ScanObjectNN OBJ_ONLY | 45 | Apr 20, 2026 | ||
| Style Transfer | ArtFID Benchmark (test) | 45 | Apr 15, 2026 | ||
| Multitask Language Understanding | MMLU physics | 45 | Apr 15, 2026 | ||
| Image Denoising | ICVL (test) | 45 | Apr 14, 2026 | ||
| Image Denoising | CAVE (test) | 45 | Apr 14, 2026 | ||
| Nudity Removal | MMA-Diffusion | 45 | Jun 30, 2026 | ||
| Fact Accuracy | Synthetic Phonebook Facts Power law Exponent beta = 0.5 | 45 | Apr 10, 2026 | ||
| Retrieval-Augmented Generation | MS MARCO | 45 | May 20, 2026 | ||
| Question Answering | GPQA Diamond | 45 | Jun 12, 2026 | ||
| Interactive Object Removal | RORD | 45 | Apr 9, 2026 | ||
| Reasoning | GSM→FOL | 45 | Apr 8, 2026 | ||
| Multimodal Reasoning | ScienceQA | 45 | May 27, 2026 | ||
| Mobile UI Control | AndroidWorld | 45 | Jun 24, 2026 | ||
| Classification | DIAGNO (test) | 45 | Apr 7, 2026 | ||
| Automatic Speech Recognition | TED-LIUM 3 | 45 | Apr 10, 2026 |