Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1118 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Compositional Reasoning | SugarCrepe++ | 25 | May 13, 2026 | ||
| 3D Hand Pose Estimation | HO-3D v2 | 25 | Mar 27, 2026 | ||
| Temporal Action Segmentation | TCG-15 | 25 | Mar 26, 2026 | ||
| Mathematical Reasoning | MATH 500 | 25 | May 18, 2026 | ||
| Object Hallucination Assessment | MSCOCO (500 random samples) | 25 | Apr 8, 2026 | ||
| Tabular Data Generation | Beijing | 25 | May 19, 2026 | ||
| Out-of-distribution detection | ImageNet FarOOD 1k | 25 | Mar 25, 2026 | ||
| Time Series Forecasting | fev-bench | 25 | May 15, 2026 | ||
| Acoustic Classification | DeepShip | 25 | Jun 2, 2026 | ||
| Tokenization Efficiency | Indic-English as (evaluation) | 25 | Mar 24, 2026 | ||
| 3D Sorting | 3D Sorting | 25 | Mar 24, 2026 | ||
| Compositional Privacy Risk Evaluation | CPRT 1.0 (test) | 25 | Mar 24, 2026 | ||
| Binary Hate Detection | FHM (test) | 25 | Mar 24, 2026 | ||
| Instruction Following | Inverse IFEval, MARS-Bench, MultiChallenge, Collie-Hard, EIFBench | 25 | Mar 24, 2026 | ||
| Mathematics | AIME-25, HMMT25(Feb), BeyondAIME, AMO-Bench, IMO-AnswerBench | 25 | Mar 24, 2026 | ||
| Faithfulness Evaluation | Faithfulness Baseline Narratives | 25 | Mar 23, 2026 | ||
| Generalized Category Discovery | CUB-200 | 25 | Jul 2, 2026 | ||
| Multiple-choice Question Answering | ARC-Easy zero-shot (test) | 25 | Mar 23, 2026 | ||
| Mathematical Reasoning | SVAMP 8-shot (test) | 25 | Mar 23, 2026 | ||
| Mathematical Reasoning | GSM8K 8-shot (test) | 25 | Mar 23, 2026 | ||
| Android malware detection | Transcendent Ramda feature space | 25 | Mar 23, 2026 | ||
| Android malware detection | Transcendent Drebin feature space | 25 | Mar 23, 2026 | ||
| Android malware detection | Hypercube Ramda feature space | 25 | Mar 23, 2026 | ||
| Android malware detection | Hypercube Drebin feature space | 25 | Mar 23, 2026 | ||
| Ultrasound Image Segmentation | DDTI | 25 | Mar 20, 2026 |