Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 846 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Prompt-induced Backdoor Attack | CST dataset | 30 | Apr 24, 2026 | ||
| SCF acceleration | QM40 (out-of-distribution) | 30 | Apr 24, 2026 | ||
| Surgical Video Question Answering | REAL-Colon-VQA (Out-of-template) | 30 | Jun 17, 2026 | ||
| Surgical Video Question Answering | REAL-Colon-VQA In-template | 30 | Jun 17, 2026 | ||
| Speculative Decoding | SQL | 30 | Apr 24, 2026 | ||
| Speculative Decoding | CNN_DM | 30 | Apr 24, 2026 | ||
| Speculative Decoding | MedQA | 30 | Apr 24, 2026 | ||
| Speculative Decoding | Chemistry | 30 | Apr 24, 2026 | ||
| Speculative Decoding | Biology | 30 | Apr 24, 2026 | ||
| Speculative Decoding | Math | 30 | Apr 24, 2026 | ||
| Speculative Decoding | Python | 30 | Apr 24, 2026 | ||
| Image Classification | CIFAR-100 70% symmetric label noise | 30 | Apr 23, 2026 | ||
| Image Classification | CIFAR-100 40% symmetric label noise | 30 | Apr 23, 2026 | ||
| Image Classification | CIFAR-100 30% symmetric label noise | 30 | Apr 23, 2026 | ||
| Stereo Matching | Middlebury Half resolution (H) | 30 | Jun 24, 2026 | ||
| Classification | CelebAMask-HQ (test) | 30 | Apr 23, 2026 | ||
| Book Plot Retrieval | NDP v1 | 30 | Apr 23, 2026 | ||
| Mathematical Reasoning | AIME 2026 | 30 | May 11, 2026 | ||
| Mathematical Reasoning | GSM8K | 30 | Apr 23, 2026 | ||
| Code Generation | MBPP | 30 | Apr 23, 2026 | ||
| Brain-to-image retrieval | THINGS-MEG Intra-subject (test) | 30 | Apr 21, 2026 | ||
| Node Classification | Cora | 30 | May 27, 2026 | ||
| Machine Unlearning | TOFU Avg. | 30 | Apr 21, 2026 | ||
| Machine Unlearning | TOFU 1% forget | 30 | Apr 21, 2026 | ||
| Machine Unlearning | TOFU 5% forget split | 30 | Apr 21, 2026 |