Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 549 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Recognition | Lacuna-10 forget split | 40 | Mar 16, 2026 | ||
| Face Recognition | Lacuna-10 (retention) | 40 | Mar 16, 2026 | ||
| Face Recognition | Lacuna-10 (test) | 40 | Mar 16, 2026 | ||
| Mathematical Reasoning | AQuA-RAT (test) | 40 | Apr 10, 2026 | ||
| Multimodal Agent Task | AgentVista | 40 | May 12, 2026 | ||
| Multimodal Agent Task | VisualToolBench | 40 | May 12, 2026 | ||
| Human position estimation | office-like environment dataset | 40 | Mar 13, 2026 | ||
| WiFi CSI sensing | factory-like environment dataset | 40 | Mar 13, 2026 | ||
| Jailbreak Attack | AdvBench-50 + Malicious Instruct | 40 | Mar 13, 2026 | ||
| Binary Classification | Credit Card (test) | 40 | Mar 23, 2026 | ||
| Coding | LiveCodeBench | 40 | Jun 9, 2026 | ||
| Image Classification | MNIST | 40 | Jun 11, 2026 | ||
| Image Classification | Stanford Cars few-shot | 40 | Jul 8, 2026 | ||
| Graph Classification | Cora v1 (target) | 40 | Mar 11, 2026 | ||
| Text-to-Speech | EmergentTTS (eval) | 40 | Jun 8, 2026 | ||
| Jailbreaking | AdvBench Sub | 40 | Mar 11, 2026 | ||
| Personalized Federated Learning | DRAKE dynamic (Others) | 40 | Mar 10, 2026 | ||
| Personalized Federated Learning | DRAKE dynamic (Self) | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | Rapel | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | Sdwpfh2 | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | Sdwpfh1 | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | Sdwpfm2 | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | Sdwpfm 1 | 40 | Mar 10, 2026 | ||
| Time Series Forecasting | BE | 40 | Mar 10, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP 100 | 40 | Jul 1, 2026 |