Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 5 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|
| Image Captioning | MS COCO Karpathy (test) | multimodalcomputer vision+1 | | 706 | May 26, 2026 |
|---|
| Image Classification | Stanford Cars | computer vision |
| 705 | Jul 2, 2026 |
|---|
| Code Generation | HumanEval (test) | code developer ai | | 701 | Jul 7, 2026 |
|---|
| Semantic Segmentation | ADE20K | computer vision | | 699 | Jul 7, 2026 |
|---|
| Natural Language Inference | SNLI (test) | nlp | | 694 | May 14, 2026 |
|---|
| Image Deblurring | GoPro (test) | computer vision | | 694 | Jun 23, 2026 |
|---|
| Image Classification | CIFAR-100 | computer vision | | 691 | Mar 10, 2026 |
|---|
| Super-Resolution | Set14 | computer vision | | 686 | Jul 7, 2026 |
|---|
| Super-resolution | Urban100 | computer vision | | 681 | Jun 25, 2026 |
|---|
| Object Detection | MS COCO (test-dev) | computer vision | | 677 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Cityscapes | computer vision | | 674 | Jun 23, 2026 |
|---|
| Person Re-identification | DukeMTMC-reID | computer vision | | 667 | May 12, 2026 |
|---|
| Multimodal Understanding | MM-Vet | multimodal | | 664 | Jun 26, 2026 |
|---|
| Action Recognition | NTU RGB+D (Cross-View) | computer vision | | 663 | Jun 4, 2026 |
|---|
| Image Classification | MNIST (test) | computer vision | | 654 | Jun 26, 2026 |
|---|
| Composed Image Retrieval | FashionIQ (val) | computer visionnlp | | 653 | Jul 2, 2026 |
|---|
| Object Detection | COCO (val) | computer vision | | 637 | Jun 19, 2026 |
|---|
| Video Understanding | MVBench | computer vision | | 635 | Jul 7, 2026 |
|---|
| Image Classification | Fashion MNIST (test) | computer vision | | 633 | Jun 2, 2026 |
|---|
| Question Answering | ARC Challenge | nlp | | 631 | Jun 24, 2026 |
|---|
| Node classification | Pubmed (test) | graph | | 628 | Jun 4, 2026 |
|---|
| Node Classification | PubMed | graph |
| 627 | Jun 2, 2026 |
|---|
| Image Super-Resolution | Set5 (test) | computer vision | | 626 | Jul 7, 2026 |
|---|
| Hallucination Detection | TriviaQA | llm chat instructionnlp |
| 625 | Jun 24, 2026 |
|---|
| Jailbreak Attack | HarmBench | adversarial safety security |
| 624 | Jul 3, 2026 |
|---|