Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1218 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Evaluation | HarmBench Contextual Trajectory Evaluation Multi-turn | 24 | Mar 18, 2026 | ||
| Emotional Support Conversation | ESC-Eval | 24 | Mar 17, 2026 | ||
| Emotional Support Conversation | EmoHarbor | 24 | Mar 17, 2026 | ||
| Emotional Support Conversation | ESConv | 24 | Mar 17, 2026 | ||
| Supervised Learning | 3D MedMNIST | 24 | Mar 17, 2026 | ||
| Supervised Learning | MedMNIST 2D | 24 | Mar 17, 2026 | ||
| New View Synthesis | DTU (R) | 24 | Mar 17, 2026 | ||
| Novel View Synthesis | DTU small-viewpoint set (R) | 24 | Mar 17, 2026 | ||
| Novel View Synthesis | LLFF small-viewpoint set (R) | 24 | Mar 17, 2026 | ||
| Long trajectory Novel View Synthesis | T&T | 24 | Mar 17, 2026 | ||
| Long trajectory Novel View Synthesis | DL3DV | 24 | Mar 17, 2026 | ||
| Long trajectory Novel View Synthesis | Mip360 | 24 | Mar 17, 2026 | ||
| Anomaly Detection | census | 24 | May 29, 2026 | ||
| Retrieval | Needle-in-a-Haystack L=8k | 24 | May 28, 2026 | ||
| Optical Character Recognition | ORB-En-FUNSD (test) | 24 | Mar 17, 2026 | ||
| Hallucination detection | FADE | 24 | Mar 17, 2026 | ||
| Hallucination detection | FaithDial | 24 | Mar 17, 2026 | ||
| Hallucination detection | BEGIN | 24 | Mar 17, 2026 | ||
| Hallucination detection | AIS | 24 | Mar 17, 2026 | ||
| Action Recognition | UCF101 VISPR | 24 | Mar 17, 2026 | ||
| Action Recognition | HMDB51 VISPR | 24 | Mar 17, 2026 | ||
| Multi-modal Tracking | VisEvent | 24 | Mar 17, 2026 | ||
| Multi-label classification | CAL500 | 24 | May 12, 2026 | ||
| Mathematical Reasoning | VisuLogic | 24 | Apr 21, 2026 | ||
| Inductive dynamic link prediction | MOOC Inductive | 24 | Mar 17, 2026 |