Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1481 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| De novo 3D molecule generation | QM9 | 21 | Jun 15, 2026 | ||
| Offline Reinforcement Learning | Walker2d | 21 | Feb 26, 2026 | ||
| Text Classification | RCV1 v2 (train) | 21 | Feb 26, 2026 | ||
| Text Classification | RCV1 v2 (val) | 21 | Feb 26, 2026 | ||
| Zero-shot Question Answering and Reasoning | Evaluation Suite Zero-shot (ARC, LogiQA, Wino, CSQA, BoolQ, PIQA, MMLU) | 21 | Feb 26, 2026 | ||
| Fraud Detection | IEEE-CIS | 21 | Jun 9, 2026 | ||
| Mathematical Reasoning | AMC | 21 | Feb 26, 2026 | ||
| EEG-based Emotion Recognition | SEED | 21 | Feb 26, 2026 | ||
| Deterministic forecasting | Solar TSFM-Bench | 21 | Feb 27, 2026 | ||
| Deterministic forecasting | ETT Avg TSFM-Bench | 21 | Feb 27, 2026 | ||
| Speaker Diarization | CallHome 2-spks with 0.25s collar tolerance (test) | 21 | Feb 26, 2026 | ||
| Commonsense Reasoning | WinoGrande 0-shot (test) | 21 | Jun 26, 2026 | ||
| QoS Prediction | WSDREAM Response Time 2T (test) | 21 | Feb 26, 2026 | ||
| Cell type classification | COVID-PBMC celltype5 (test) | 21 | Feb 26, 2026 | ||
| Missing Data Imputation | Exchange (test) | 21 | Feb 26, 2026 | ||
| Vehicle Routing Problem | CVRP n=50 | 21 | May 1, 2026 | ||
| Outlier Detection | Wilt | 21 | Mar 17, 2026 | ||
| Out-of-Distribution Detection | Places365 | 21 | Apr 7, 2026 | ||
| Intrusion Detection | TON_IoT | 21 | Jun 23, 2026 | ||
| Multimodal Classification | UKB | 21 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE original (val) | 21 | May 13, 2026 | ||
| Rubric satisfaction evaluation | Medical | 21 | Feb 26, 2026 | ||
| Rubric satisfaction evaluation | ArXiv | 21 | Feb 26, 2026 | ||
| Node classification | CoraML | 21 | Jun 12, 2026 | ||
| Delivery Decision Policy Evaluation | Synthetic Urban Service Region | 21 | Feb 26, 2026 |