Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1429 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Classification | Arxiv Semi-Synthetic | 21 | Jun 16, 2026 | ||
| Node Classification | PubMed Semi-Synthetic | 21 | Jun 16, 2026 | ||
| Node Classification | Cora Semi-Synthetic | 21 | Jun 16, 2026 | ||
| Negative Query Recognition | CoMET-Bench | 21 | Jun 16, 2026 | ||
| Temporal Grounding | CoMET-Bench | 21 | Jun 16, 2026 | ||
| Counting | CoMET-Bench | 21 | Jun 16, 2026 | ||
| Robotic Manipulation Success | GAPartNet | 21 | Jun 16, 2026 | ||
| Semantic Segmentation | RANUS NIR Exterior (val) | 21 | Jun 16, 2026 | ||
| Semantic Segmentation | Interior NIR (val) | 21 | Jun 16, 2026 | ||
| Image Classification | ImageNet 1K | 21 | Jun 16, 2026 | ||
| Anti-spoofing | Aggregate of Anti-spoofing Corpora | 21 | Jun 15, 2026 | ||
| Forecasting under missing-at-random observations | D1 advection–diffusion | 21 | Jun 15, 2026 | ||
| Deep Research | HealthBench ResearchQA DRB Macro Average | 21 | Jun 15, 2026 | ||
| Deep Research | DeepResearchBench (DRB) | 21 | Jun 15, 2026 | ||
| Mathematical Reasoning | Aggregated Mathematical Reasoning Datasets (AIME24, AIME25, AMC23, MATH500, Minerva, Olympiad) | 21 | Jun 12, 2026 | ||
| Time-series forecasting | TimesFM Weather 2.5 (test) | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario D 5% contamination | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario C 5% contamination | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario B 5% contamination | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario A 5% contamination | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario D | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario C | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario B | 21 | Jun 12, 2026 | ||
| Temporal Clustering | Scenario A | 21 | Jun 12, 2026 | ||
| Image Classification | Cars196 | 21 | Jun 12, 2026 |