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 |
|---|---|---|---|---|---|
| Sound Speed Profile estimation | SSP data at 1976m depth 2021.01-2023.06 (test) | 44 | Mar 24, 2026 | ||
| LLM-as-a-Judge | MT-Bench | 44 | Apr 23, 2026 | ||
| Mathematical Reasoning | GSM-sym | 44 | Apr 20, 2026 | ||
| Novel View Synthesis | Tanks&Temples | 44 | May 1, 2026 | ||
| Class-conditional Image Generation | ImageNet 256 |
| 44 |
| Jun 29, 2026 |
| Bi-objective Traveling Salesman Problem | Bi-TSP50 | 44 | May 25, 2026 |
|---|
| Tri-Objective Traveling Salesman Problem | Tri-TSP50 | 44 | May 25, 2026 |
|---|
| Multi-Objective Traveling Salesperson Problem | KroAB200 | 44 | May 25, 2026 |
|---|
| Multi-Objective Traveling Salesperson Problem | KroAB150 | 44 | May 25, 2026 |
|---|
| Multi-Objective Traveling Salesperson Problem | KroAB100 | 44 | May 25, 2026 |
|---|
| Robotic task execution | LIBERO | 44 | Jun 1, 2026 |
|---|
| Recommendation | RetailRocket | 44 | Apr 20, 2026 |
|---|
| Novel View Synthesis | T&T small-viewpoint set (O) | 44 | Mar 17, 2026 |
|---|
| Classification | BRACS | 44 | Apr 9, 2026 |
|---|
| Unconditional image generation | CIFAR-10 32x32 EDM (test) | 44 | Mar 17, 2026 |
|---|
| Unconditional Image Generation | CIFAR-10 32x32 Score-SDE 50k samples (test) | 44 | Mar 17, 2026 |
|---|
| Image Generation | ImageNet 64x64 (50k samples) | 44 | Mar 17, 2026 |
|---|
| Text-to-image generation | Stable Diffusion 10k samples v1.4 (test) | 44 | Mar 17, 2026 |
|---|
| Camouflaged Object Detection | CAMO | 44 | Apr 15, 2026 |
|---|
| Multiple-choice Question Answering | GPQA | 44 | Apr 23, 2026 |
|---|
| Creative Writing | Creative Writing v3 | 44 | Jun 25, 2026 |
|---|
| Salient Object Detection | ORSSD | 44 | Jun 9, 2026 |
|---|
| Image Classification | ImageNet, Caltech101, DTD, EuroSAT, FGVCAircraft, Food101, OxfordFlowers, OxfordPets, StanfordCars, SUN397, UCF101 1-shot | 44 | Jul 2, 2026 |
|---|
| Confidence Calibration | vehicle | 44 | Mar 12, 2026 |
|---|
| Confidence Calibration | glass | 44 | Mar 12, 2026 |
|---|