Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 678 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Hallucination Evaluation | MSCOCO | 35 | Mar 31, 2026 | ||
| Vision-and-Language Navigation | R2R-CE unseen continuous (val) | 35 | Apr 1, 2026 | ||
| Image Restoration | MiO100 AgenticIR setting (Group C) | 35 | May 22, 2026 | ||
| Natural Language Inference | NLI benchmarks (MNLI, QNLI, SNLI, RTE, SICK, SCITAIL) (test) | 35 | Jun 4, 2026 | ||
| CTR Prediction | Taobao 1.68% compression | 35 | Mar 27, 2026 | ||
| CTR Prediction | Tmall 1.39% compression | 35 | Mar 27, 2026 | ||
| CTR Prediction | KuaiRand 1.50% compression | 35 | Mar 27, 2026 | ||
| Face Forgery Detection | CDF v2 (test) | 35 | Jul 7, 2026 | ||
| Deepfake Detection | DF40 (test) | 35 | Apr 7, 2026 | ||
| 3D Shape Matching | SCAPE S | 35 | Mar 25, 2026 | ||
| 3D Shape Matching | FAUST (F) | 35 | Mar 25, 2026 | ||
| Spatial Reasoning | SPARTUN | 35 | Jul 1, 2026 | ||
| Species Classification | Animal audio species dataset unseen species (test) | 35 | Mar 24, 2026 | ||
| Novel View Synthesis | DL3DV 24 views | 35 | Jul 9, 2026 | ||
| Gaze Estimation | Gaze360 | 35 | Jun 11, 2026 | ||
| No-reference Image Quality Assessment | PIPAL | 35 | Jun 12, 2026 | ||
| Argument Classification | Args.me | 35 | Mar 23, 2026 | ||
| Surface Reconstruction | DTU (test) | 35 | May 13, 2026 | ||
| Information Retrieval | ArguAna BEIR | 35 | Jun 29, 2026 | ||
| Surgical Scene Segmentation | EndoVis 2018 (ID) | 35 | Mar 20, 2026 | ||
| Generative Modeling | CIFAR-10 | 35 | Apr 28, 2026 | ||
| Video Reasoning | VBVR-Bench In-Domain | 35 | Jun 2, 2026 | ||
| Multi-behavior Recommendation | Tmall | 35 | Jun 2, 2026 | ||
| Object Detection | PASCAL C | 35 | May 6, 2026 | ||
| Cross-View Object Geo-Localization (Drone → Satellite) | CVOGL R (test) | 35 | Mar 17, 2026 |