Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1158 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Future edge prediction | ENRON DyGLib (inductive) | 24 | Jul 7, 2026 | ||
| Future edge prediction | MOOC DyGLib (inductive) | 24 | Jul 7, 2026 | ||
| Multi-task Language Model Evaluation | TÜLU Evaluation Suite (MMLU, TQA, PopQA, BBH, DROP, CHE, CHE+, GSM8K, MATH, IFEval) 2/3 | 24 | Jul 7, 2026 | ||
| Hallucination monitoring | Treatment domain | 24 | Jul 7, 2026 | ||
| Image Classification | IN-100 | 24 | Jul 3, 2026 | ||
| Image Classification | PAINT | 24 | Jul 3, 2026 | ||
| Image Classification | Disentangling | 24 | Jul 3, 2026 | ||
| Image Classification | RTA-100 | 24 | Jul 3, 2026 | ||
| Static Skill Scanner Evasion | Skill Scanners Evaluation Suite | 24 | Jul 3, 2026 | ||
| Image Generation | MNIST | 24 | Jul 3, 2026 | ||
| One-dimensional diffusion sampling | One-dimensional experiment | 24 | Jul 3, 2026 | ||
| Circuit discovery | Induction | 24 | Jul 3, 2026 | ||
| Circuit discovery | Previous-token | 24 | Jul 3, 2026 | ||
| Circuit discovery | Duplicate-token | 24 | Jul 3, 2026 | ||
| Speaker Verification | VoxCeleb1-50 | 24 | Jul 3, 2026 | ||
| Speaker Verification | AISHELL3 50 | 24 | Jul 3, 2026 | ||
| Speech Emotion Recognition | ESD EN | 24 | Jul 3, 2026 | ||
| Speech Emotion Recognition | ESD CN | 24 | Jul 3, 2026 | ||
| Zero-shot Evaluation | MMLU, GSM, M500 (test) | 24 | Jul 3, 2026 | ||
| Text Reasoning | In-domain (test) | 24 | Jul 3, 2026 | ||
| Articulatory-to-Acoustic Inversion | EMA seen speakers (test) | 24 | Jul 3, 2026 | ||
| Articulatory-to-Acoustic Inversion (AAI) | EMA dataset unseen speakers (test) | 24 | Jul 3, 2026 | ||
| Filtering | Lorenz-96 Arctangent Observation Operator | 24 | Jul 2, 2026 | ||
| Filtering | Lorenz-96 | 24 | Jul 2, 2026 | ||
| Hallucination Detection | Hallucination-detection dataset | 24 | Jul 2, 2026 |