Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1315 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Driver Drowsiness Estimation | SEED-VIG | 23 | Mar 18, 2026 | ||
| Video reasoning | EgoSchema (test) | 23 | May 26, 2026 | ||
| Vision-Language Navigation | AerialVLN unseen S (val) | 23 | Apr 21, 2026 | ||
| Vision-Language Navigation | AerialVLN S (val seen) | 23 | Apr 21, 2026 | ||
| 3D Object Classification | ScanObjectNN OBJ_ONLY FULL Protocol | 23 | Feb 26, 2026 | ||
| 3D Object Classification | ScanObjectNN OBJ_BG (FULL Protocol) | 23 | Feb 26, 2026 | ||
| Novel View Synthesis | Tank & Temples (test) | 23 | Feb 26, 2026 | ||
| Image Classification | PCAM | 23 | Apr 23, 2026 | ||
| Video Understanding | VSI-Bench | 23 | May 19, 2026 | ||
| Pose Estimation | ACID | 23 | Mar 31, 2026 | ||
| Image Classification | EuroSAT | 23 | Mar 10, 2026 | ||
| Face Presentation Attack Detection | OULU-NPU Target (test) | 23 | Jul 3, 2026 | ||
| Camouflaged Object Detection | COD10K 1.0 (test) | 23 | Feb 26, 2026 | ||
| Camouflaged Object Detection | CAMO 1.0 (test) | 23 | Feb 26, 2026 | ||
| Date Estimation | YearGuessr (test) | 23 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | OpenUAV Full (test seen) | 23 | Jul 1, 2026 | ||
| Image Denoising | IOCI | 23 | Feb 26, 2026 | ||
| Audio-Video Understanding | OmniVideoBench | 23 | May 19, 2026 | ||
| Point Cloud Quality Assessment | PCQA Oc (Octree-based Compression Distortion) | 23 | Feb 26, 2026 | ||
| Video Hallucination Assessment | VideoHallucer | 23 | May 12, 2026 | ||
| Text-to-Video Generation | HunyuanVideo (test) | 23 | Jun 5, 2026 | ||
| Semantic Segmentation | ScanNet 19 classes | 23 | Jul 2, 2026 | ||
| Visual Counting | CountBench 13 (test) | 23 | Feb 26, 2026 | ||
| Mathematical Reasoning | MathVista 96 (testmini) | 23 | Feb 26, 2026 | ||
| Visual Question Answering | RWQA 158 (val) | 23 | Feb 26, 2026 |