Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1556 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| LLM Alignment | EduFeedback | 20 | May 25, 2026 | ||
| Inversion Attack Recovery | iCliniq | 20 | May 25, 2026 | ||
| Inversion Attack Recovery | AlpacaEval | 20 | May 25, 2026 | ||
| Reconstruction Privacy Evaluation | iCliniq (test) | 20 | May 25, 2026 | ||
| Reconstruction Privacy Evaluation | AlpacaEval (test) | 20 | May 25, 2026 | ||
| Monocular Depth Estimation | ScanNet (100 sequences) | 20 | May 25, 2026 | ||
| Mathematical Reasoning | AIME 25 | 20 | May 25, 2026 | ||
| Aircraft Maintenance Task Scheduling | Boeing 737NG-600 instances | 20 | May 25, 2026 | ||
| Multi-agent Sequential Communication | AgentLeak | 20 | May 22, 2026 | ||
| Question Answering | MMLU | 20 | May 22, 2026 | ||
| Code Generation | CodeAlpaca 20k | 20 | May 22, 2026 | ||
| Text-to-Image Generation | Aesthetic-4K (test) | 20 | May 22, 2026 | ||
| Math Problem Solving | MMATH (test) | 20 | May 22, 2026 | ||
| Closed-loop Collaborative Driving | CARLA Town05 | 20 | May 22, 2026 | ||
| Scientific Question Answering | GPQA Main (test) | 20 | May 22, 2026 | ||
| Mathematical Reasoning | Olympiad | 20 | May 22, 2026 | ||
| Mathematical Reasoning | AMC 23 | 20 | May 22, 2026 | ||
| Mathematical Reasoning | Minerva | 20 | May 22, 2026 | ||
| Mathematical Reasoning | MATH500 | 20 | May 22, 2026 | ||
| Mathematical Reasoning | GSM8K | 20 | May 22, 2026 | ||
| Generalized Category Discovery | CIFAR10, CIFAR100, ImageNet-100 | 20 | May 22, 2026 | ||
| Receipt Information Extraction | ReceiptBench 1.0 (test) | 20 | May 22, 2026 | ||
| Emotion Recognition | SEED | 20 | Jun 2, 2026 | ||
| Visual Question Answering | GQA | 20 | Jul 1, 2026 | ||
| Linear regression | Santander | 20 | May 22, 2026 |