Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1539 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Transfer Learning | SPHER | 20 | Jun 16, 2026 | ||
| Audio-Visual Video Understanding | OmniVideoBench truncated <= 5min | 20 | Jun 15, 2026 | ||
| Factor Discovery | Tushare Pro A-share (2022-2026) | 20 | Jun 15, 2026 | ||
| Combinatorial Optimization | BPP-ACO | 20 | Jun 15, 2026 | ||
| Combinatorial Optimization | TSP-ACO | 20 | Jun 15, 2026 | ||
| Dynamic state estimation | piecewise non-stationary LiDAR trajectories (test) | 20 | Jun 15, 2026 | ||
| Eigenvalue Estimation | Van der Pol (VDP) Oscillator | 20 | Jun 15, 2026 | ||
| AI-generated text detection and calibration | DetectRL Prompt attack | 20 | Jun 15, 2026 | ||
| Robotics Task Execution | RoboTwin 2.0 (Clean) | 20 | Jun 19, 2026 | ||
| Span and Type Prediction | Drug-ACE (test) | 20 | Jun 15, 2026 | ||
| Span Prediction | Drug-ACE (test) | 20 | Jun 15, 2026 | ||
| ICD Coding | MIMIC-III (full) | 20 | Jun 15, 2026 | ||
| ICD Coding | MIMIC Full IV | 20 | Jun 15, 2026 | ||
| Information Retrieval | BRIGHT (test) | 20 | Jun 15, 2026 | ||
| Question Answering | OpenBookQA | 20 | Jun 15, 2026 | ||
| Question Classification | TREC50 | 20 | Jun 15, 2026 | ||
| Image Classification | CIFAR-10 | 20 | Jun 15, 2026 | ||
| Question Answering | OpenBookQA | 20 | Jun 15, 2026 | ||
| Image Classification | CIFAR-10 | 20 | Jun 15, 2026 | ||
| Data-to-text Generation | E2E | 20 | Jun 15, 2026 | ||
| Logical Reasoning | FOLIO | 20 | Jun 15, 2026 | ||
| Refusal Suppression | VLSBench | 20 | Jun 15, 2026 | ||
| Refusal Suppression | JailbreakV-28K | 20 | Jun 15, 2026 | ||
| Refusal Suppression | StrongREJECT | 20 | Jun 15, 2026 | ||
| Refusal Suppression | AdvBench | 20 | Jun 15, 2026 |