Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1348 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Verification | RFW | 22 | Jun 4, 2026 | ||
| Face Verification Accuracy and Calibration | RFW (test) | 22 | Jun 4, 2026 | ||
| Face Verification Fairness Evaluation | BFW (test) | 22 | Jun 4, 2026 | ||
| Long-context understanding | LongBench | 22 | Jun 4, 2026 | ||
| Retrieval | Needle-in-A-Haystack RULER | 22 | Jun 4, 2026 | ||
| Remote Sensing Change Captioning | LEVIR-CC | 22 | Jul 7, 2026 | ||
| Privacy Parameter Estimation | Cora 50% nodes sampled (train) | 22 | Jun 4, 2026 | ||
| Star discrepancy estimation | sequences various configurations | 22 | Jun 4, 2026 | ||
| Node Classification | Products (test) | 22 | Jun 4, 2026 | ||
| Multi-Hop Question Answering | HotpotQA | 22 | Jul 8, 2026 | ||
| Subtask 1 | SemEval | 22 | Jun 4, 2026 | ||
| Causal Discovery | Flood CausalRiver | 22 | Jun 4, 2026 | ||
| Knowledge Editing | MQuAKE-T | 22 | Jun 4, 2026 | ||
| Image Classification | MetaShift Cat vs. Dog 18 (test) | 22 | Jun 4, 2026 | ||
| Domain Generalization | MetaShift Animals 8-class (test) | 22 | Jun 4, 2026 | ||
| Spatial decision-making | Maze size 8 | 22 | Jun 4, 2026 | ||
| Robust Classification | Waterbirds (test) | 22 | Jun 23, 2026 | ||
| Single-Hop Question Answering | NQ (test) | 22 | Jul 7, 2026 | ||
| Tool Using | Non-Live P-Mul | 22 | Jun 2, 2026 | ||
| Tool Using | Non-Live Para | 22 | Jun 2, 2026 | ||
| Tool Using | Live P-Mul | 22 | Jun 2, 2026 | ||
| Tool Using | Live Para | 22 | Jun 2, 2026 | ||
| General Performance | Aggregated Benchmarks | 22 | Jun 2, 2026 | ||
| State Estimation | UIP-DB | 22 | Jun 2, 2026 | ||
| Visual Place Recognition | Pitts30k (test) | 22 | Jun 2, 2026 |