Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1173 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Remaining Useful Life Prediction | C-MAPSS FD004 (test) | 24 | Jun 2, 2026 | ||
| Remaining Useful Life Prediction | C-MAPSS FD003 (test) | 24 | Jun 2, 2026 | ||
| Semantic Segmentation | Cityscapes 16 classes (val) | 24 | Jun 2, 2026 | ||
| Knowledge & Instruction Following | MMLU | 24 | Jun 2, 2026 | ||
| Future Motion Segmentation | EVIMO | 24 | Jun 2, 2026 | ||
| Response Generation | UltraFeedback (val) | 24 | Jun 2, 2026 | ||
| Model Inversion Defense | CelebA 64x64 (test) | 24 | Jun 2, 2026 | ||
| Time Series Forecasting | Walker MuJoCo D (test) | 24 | Jun 2, 2026 | ||
| Time Series Forecasting | Hopper MuJoCo D (test) | 24 | Jun 2, 2026 | ||
| Constrained Black-box Optimization | 9 Tabular Benchmarks Constraint: Runtime | 24 | Jun 2, 2026 | ||
| Constrained Black-box Optimization | 9 Tabular Benchmarks Constraint: Network size | 24 | Jun 2, 2026 | ||
| Constrained Black-box Optimization | 9 Tabular Benchmarks Constraint: Runtime & Network size | 24 | Jun 2, 2026 | ||
| Poverty Index Regression | PovertyMap (test) | 24 | Jun 2, 2026 | ||
| Fine-grained visual perception | OCRBench (test) | 24 | Jun 2, 2026 | ||
| Visual Question Answering | Super-CLEVR (test) | 24 | Jun 2, 2026 | ||
| Visual Question Answering | ChartQA EvoCharts (test) | 24 | Jun 2, 2026 | ||
| Certified Robustness | MNIST | 24 | Jun 29, 2026 | ||
| Sequential Recommendation | LastFM | 24 | Jun 2, 2026 | ||
| Sequential Recommendation | All Beauty | 24 | Jun 2, 2026 | ||
| Persuasion | Cornell CMV Persuadee: LLaMa3.1 OOD | 24 | Jun 2, 2026 | ||
| Persuasion | Cornell CMV Persuadee: Qwen2.5 | 24 | Jun 2, 2026 | ||
| Makespan Accuracy | AsyncPlan-XXL | 24 | Jun 2, 2026 | ||
| Emotion Recognition | SEED v1 (cross-subject) | 24 | Jun 2, 2026 | ||
| Sequential Conformal Prediction | Weather Rain | 24 | Jun 2, 2026 | ||
| Social omnimodal reasoning | Social Omni | 24 | Jun 2, 2026 |