Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Image Denoising | McMaster | 35 | Apr 21, 2026 | ||
| Natural Language Understanding | HellaSwag | 35 | May 21, 2026 | ||
| LiDAR Localization | Oxford (17-13-26-39) | 35 | Jun 29, 2026 | ||
| LiDAR Localization | Oxford (15-13-06-37) | 35 | Jun 29, 2026 | ||
| Automatic Speech Recognition | Librispeech | 35 | May 12, 2026 | ||
| VGGFace2 |
| 35 |
| Feb 26, 2026 |
| No-Reference Image Quality Assessment | KonIQ-10k (test) | 35 | Mar 17, 2026 |
|---|
| Language Modeling | Text8 (test) | 35 | May 14, 2026 |
|---|
| Gaussian Deblurring | CelebA | 35 | May 14, 2026 |
|---|
| Fraud Detection | YelpChi (test) | 35 | Mar 11, 2026 |
|---|
| Visual Grounding | ScanRefer v1 (val) | 35 | May 11, 2026 |
|---|
| Image Classification | CIFAR-100 0.35% BER (test) | 35 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-100 0.5% BER (test) | 35 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-100 1% BER (test) | 35 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-10 0.5% BER (test) | 35 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-10 1% BER (test) | 35 | Feb 26, 2026 |
|---|
| Automatic Speech Recognition | KeSpeech | 35 | May 12, 2026 |
|---|
| Scene Text Recognition | Uber-Text (test) | 35 | Feb 26, 2026 |
|---|
| Action Recognition | NTU-60 (x-sub) | 35 | Mar 12, 2026 |
|---|
| Medical Image Classification | OrgancMnist MedMnist (test) | 35 | Feb 26, 2026 |
|---|
| Medical Image Classification | APTOS 2019 (test) | 35 | Feb 26, 2026 |
|---|
| Sentiment Classification | Mpqa | 35 | Mar 5, 2026 |
|---|
| Text-to-Image Generation | HPSv2 | 35 | Feb 26, 2026 |
|---|
| Language Modeling | PTB zero-shot | 35 | Jun 9, 2026 |
|---|
| Flood Detection | WBS-SI | 35 | Apr 20, 2026 |
|---|