Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 937 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Search behavior prediction | JDSearch | 28 | May 11, 2026 | ||
| Online Bin Packing | Online BPP Weibull-5k (test) | 28 | May 11, 2026 | ||
| Referring Audio-Visual Segmentation | Ref-AVS (mix) | 28 | May 15, 2026 | ||
| Referring Audio-Visual Segmentation | Ref-AVS (unseen) | 28 | May 15, 2026 | ||
| Reaction Feasibility Prediction | FREA Infeasible 1.0 (test) | 28 | May 11, 2026 | ||
| Reaction Feasibility Prediction | FREA Feasible 1.0 (test) | 28 | May 11, 2026 | ||
| Reaction Feasibility Prediction | FREA Overall 1.0 (test) | 28 | May 11, 2026 | ||
| Sample-level Membership Inference | LIBERO Object | 28 | May 11, 2026 | ||
| Sample-level Membership Inference | LIBERO Goal | 28 | May 11, 2026 | ||
| Harmful Action Evaluation | Insider Threat | 28 | May 11, 2026 | ||
| Safety Evaluation | SafetyBench | 28 | May 11, 2026 | ||
| Safety evaluation | TRIDENT | 28 | May 11, 2026 | ||
| Factuality Question Answering | TruthfulQA | 28 | May 11, 2026 | ||
| Graph classification (trajectory- vs cluster-like) | Single-cell graphs All Graphs (full set) | 28 | May 8, 2026 | ||
| Concept-based Steering | AXBENCH (test) | 28 | May 8, 2026 | ||
| Question Answering | CoQA | 28 | May 8, 2026 | ||
| Hallucination Correction | TruthfulQA gated mode (test) | 28 | May 8, 2026 | ||
| Urban Path Generation | Melb 88 POIs | 28 | May 8, 2026 | ||
| Urban Path Generation | Toro 29 POIs | 28 | May 8, 2026 | ||
| Urban Path Generation | Edin 28 POIs | 28 | May 8, 2026 | ||
| Fashion style classification | FashionStyle14 16-shot | 28 | May 8, 2026 | ||
| Fashion style classification | FashionStyle14 8-shot | 28 | May 8, 2026 | ||
| Fashion style classification | FashionStyle14 4-shot | 28 | May 8, 2026 | ||
| Fashion style classification | FashionStyle14 2-shot | 28 | May 8, 2026 | ||
| Fashion style classification | FashionStyle14 1-shot | 28 | May 8, 2026 |