Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1176 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | Email Spam | 24 | May 29, 2026 | ||
| Long Video Understanding | LongVideoBench | 24 | May 29, 2026 | ||
| Egocentric Video Understanding | EgoSchema | 24 | May 29, 2026 | ||
| Memory Poisoning Attack | Financial Agent | 24 | May 29, 2026 | ||
| Memory Poisoning Attack | Medical Agent | 24 | May 29, 2026 | ||
| Memory Poisoning Attack | Personal Agent | 24 | May 29, 2026 | ||
| Membership Inference | LIMR | 24 | May 29, 2026 | ||
| Membership Inference | Eurus | 24 | May 29, 2026 | ||
| EEG Super-Resolution | SEED-IV 62 ch. | 24 | May 29, 2026 | ||
| EEG Super-Resolution | SEED 62 ch. | 24 | May 29, 2026 | ||
| Watermark Removal | CelebA-HQ LoRA, w/o te | 24 | May 29, 2026 | ||
| Image Classification | CIFAR-10 (2-way sharded split) | 24 | May 29, 2026 | ||
| Factual QA | SimpleQA | 24 | May 29, 2026 | ||
| 3D Gaussian Splatting Watermarking | Blender and LLFF (test) | 24 | May 29, 2026 | ||
| Blockchain Anomaly Detection | AlphaHomora (test) | 24 | May 29, 2026 | ||
| Image Classification | CIFAR-100 | 24 | May 29, 2026 | ||
| Inductive dynamic link prediction | UN Vote | 24 | Jun 4, 2026 | ||
| Photonic Inverse Design | PCF design tasks | 24 | May 29, 2026 | ||
| Logical planning | Countdown (test) | 24 | May 29, 2026 | ||
| Logical planning | Sudoku (test) | 24 | May 29, 2026 | ||
| Mathematical Reasoning | AIME 25 | 24 | May 29, 2026 | ||
| Mathematical Reasoning | MATH 500 | 24 | May 29, 2026 | ||
| CTR Prediction | KuaiVideo BARS-tuned (test) | 24 | May 29, 2026 | ||
| Instruction Following Evaluation | PPE-IFEval | 24 | May 29, 2026 | ||
| Transaction ordering | Synthetic trade sequences log-normal distribution (1,000 trials per n) | 24 | May 29, 2026 |