Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 803 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Learning | COCO-SP | 31 | Jun 4, 2026 | ||
| Graph Learning | VOC-SP | 31 | Jun 4, 2026 | ||
| Graph Learning | CLUSTER | 31 | Jun 4, 2026 | ||
| Graph Learning | PATTERN | 31 | Jun 4, 2026 | ||
| Sphere Kissing Problem | Sphere Kissing Problem | 31 | Jun 4, 2026 | ||
| Large Language Model Pruning Calibration | OIT-PC Evaluation Suite | 31 | Jun 4, 2026 | ||
| PDE Solving | Darcy flow (val) | 31 | Jun 4, 2026 | ||
| General Language Understanding | NLU Suite (MMLU, SST-2, AGNews, 20News, MNLI, SNLI) | 31 | Jun 4, 2026 | ||
| Concept Erasure | GCD v1.4 (test) | 31 | Jun 2, 2026 | ||
| Object Erasure | CIFAR-10 v1 (test) | 31 | Jun 2, 2026 | ||
| Image-to-text | COCO | 31 | Jun 2, 2026 | ||
| Zero-shot General Evaluation | Zero-shot Task Suite (HellaSwag, MathQA, MMLU, OpenBookQA, WinoGrande, GSM8K, HumanEval) | 31 | Jun 2, 2026 | ||
| Image Compression | Kodak | 31 | May 29, 2026 | ||
| Closed-loop motion planning | nuPlan 14-Hard (test) | 31 | Jun 9, 2026 | ||
| Automatic Speech Recognition | UIT-ViMD (test) | 31 | May 28, 2026 | ||
| General Multimodal Understanding | MMMU Pro | 31 | Jun 9, 2026 | ||
| Defocus Deblurring | DPDD (test) | 31 | Jul 8, 2026 | ||
| Knowledge Graph Question Answering | QALD-10en Wikidata-based (test) | 31 | Jun 2, 2026 | ||
| Knowledge Graph Question Answering | SimpleQA Freebase-based (test) | 31 | Jun 2, 2026 | ||
| Entity Regression (study-adverse) | rel trial | 31 | Jun 9, 2026 | ||
| Adversarial Attack | ImageNet-1K ILSVRC 2012 | 31 | May 21, 2026 | ||
| Audio-visual understanding | Audio-visual understanding evaluation suite (WorldSense, Daily-Omni, OmniVideoBench, Video-MME, and LVOmniBench) (test) | 31 | May 20, 2026 | ||
| Language adaptation | Galician | 31 | May 20, 2026 | ||
| Multimodal Capability Evaluation | MMStar | 31 | Jun 26, 2026 | ||
| Classification | Synthetic | 31 | Jun 1, 2026 |