Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1350 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-context reasoning | LongGenBench 4K | 22 | May 29, 2026 | ||
| Risk Stratification | Retrospective multimodal cardiovascular clinical decision-making dataset (test) | 22 | May 29, 2026 | ||
| Image Classification | CIFAR-10 balanced setting (test) | 22 | May 29, 2026 | ||
| Android GUI Automation | AndroidWorld M | 22 | May 29, 2026 | ||
| GUI Agent Interaction | Memory-World (test) | 22 | May 29, 2026 | ||
| Natural Language Graph Reasoning | NLGraph (test) | 22 | May 29, 2026 | ||
| Natural Language Graph Reasoning | NLGraph (val) | 22 | May 29, 2026 | ||
| Knowledge Reasoning | K-Cross (test) | 22 | May 29, 2026 | ||
| Knowledge Reasoning | K-Cross (val) | 22 | May 29, 2026 | ||
| Forgery detection | Celeb-DF v2 | 22 | May 29, 2026 | ||
| Forgery detection | DFDCP | 22 | May 29, 2026 | ||
| Object Hallucination Detection | Object Hall-Bench | 22 | May 29, 2026 | ||
| Symbolic Regression | Lung Cancer with Chemo & Radio (LC-CR) (test) | 22 | May 29, 2026 | ||
| Personalized News Categorization | LaMP 2N | 22 | Jun 4, 2026 | ||
| Personalized Movie Tagging | LaMP-2M | 22 | Jun 4, 2026 | ||
| Personalized Citation Identification | LaMP-1 | 22 | Jun 4, 2026 | ||
| Personalized Scholarly Title Generation | LaMP-5 v1 (test) | 22 | Jun 4, 2026 | ||
| Personalized News Headlines Generation | LaMP-4 v1 (test) | 22 | Jun 4, 2026 | ||
| Time-series forecasting | M5 items | 22 | May 28, 2026 | ||
| Time-series forecasting | M4 monthly | 22 | May 28, 2026 | ||
| Multimodal Understanding and Question Answering | LLaVA 7B Evaluation Suite (GQA, MMBench, MMBench-CN, MME, POPE, ScienceQA, VQAv2, TextVQA, SEED-Bench, VizWiz) 1.5 | 22 | May 28, 2026 | ||
| Mask-prediction (MASK_FORECAST_25) | Function-Composition Tier 1 ID | 22 | May 28, 2026 | ||
| Multimodal Understanding | VMCBench | 22 | Jun 19, 2026 | ||
| Chess move prediction | ABB (first 10 plies omitted) | 22 | May 28, 2026 | ||
| Mathematical Reasoning | MATH500, AIME24, AIME25, AMC23 | 22 | May 28, 2026 |