Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 570 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Capability Retention | Held-out capability AIME-2024, MATH-500, GSM8K, HumanEval, MMLU (test) | 39 | May 19, 2026 | ||
| Machine Translation | NTREX-128 | 39 | May 18, 2026 | ||
| Multi-domain reasoning | BBH | 39 | Jun 5, 2026 | ||
| Downstream Task Evaluation | DS-Avg 9 downstream tasks suite | 39 | May 15, 2026 | ||
| Face Verification | FDF (test) | 39 | May 14, 2026 | ||
| Image Classification | Oxford-IIIT Pet | 39 | Jun 2, 2026 | ||
| Text Classification | AG News | 39 | May 13, 2026 | ||
| Multi-turn Dialogue Generation | MT-bench | 39 | Jul 1, 2026 | ||
| Long-form research | DRB | 39 | May 18, 2026 | ||
| Machine Unlearning | CIFAR10 Subclass airplane (test) | 39 | May 12, 2026 | ||
| Mathematical Problem Solving | AIME 25 | 39 | May 12, 2026 | ||
| Mathematical Problem Solving | MATH | 39 | May 12, 2026 | ||
| Node Classification | Elo-Photo (test) | 39 | May 12, 2026 | ||
| Short-answer Question Answering | HotPotQA | 39 | Jun 12, 2026 | ||
| Image Classification | DTD | 39 | Jun 24, 2026 | ||
| Classification | CNAE high-dimensional and sparse (test) | 39 | May 12, 2026 | ||
| Tabular Analysis | WTQ | 39 | Jun 11, 2026 | ||
| Long-term forecasting | Traffic | 39 | May 27, 2026 | ||
| Sample-level Membership Inference | LIBERO Spatial | 39 | Jun 16, 2026 | ||
| Training data detection | S 1.1 | 39 | May 11, 2026 | ||
| Training data detection | LIMO | 39 | May 11, 2026 | ||
| Training data detection | S1 | 39 | May 11, 2026 | ||
| Distillation data detection | S 1.1 | 39 | May 11, 2026 | ||
| Distillation data detection | LIMO | 39 | May 11, 2026 | ||
| Mathematical Reasoning | BeyondAIME | 39 | Jun 9, 2026 |