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 |
|---|---|---|---|---|---|
| Personalization | Community Alignment (CA) | 45 | Mar 23, 2026 | ||
| Object Detection | property risk detection | 45 | Mar 20, 2026 | ||
| Clustering | Gisette | 45 | Mar 19, 2026 | ||
| Context-guided time series forecasting | PTF | 45 | Mar 18, 2026 | ||
| Dynamic Object Detection | Real-world indoor dynamic human obstacles 1.0 (test) | 45 | Mar 18, 2026 |
| Scene Deformation | NeRF Synthetic NeuralEditor benchmark deformation task (test) | 45 | Mar 17, 2026 |
|---|
| Tool-use | τ-Bench | 45 | Jun 12, 2026 |
|---|
| Math Reasoning | MATH 500 | 45 | Jun 18, 2026 |
|---|
| Over-refusal Evaluation | XSTest Safe | 45 | Jun 16, 2026 |
|---|
| Watermark similarity restoration | DenseNet 0.2 NSO cat-ops attack ratio | 45 | Mar 16, 2026 |
|---|
| Watermark similarity restoration | InceptionV3 0.2 NSO cat-ops attack ratio | 45 | Mar 16, 2026 |
|---|
| Polish Instruction Following | Open PL LLM Leaderboard | 45 | Mar 13, 2026 |
|---|
| AI-generated image detection | GenImage 61 (test) | 45 | Mar 13, 2026 |
|---|
| Disease Classification | CheXpert | 45 | Jun 4, 2026 |
|---|
| Multimodal Mathematical Reasoning | DynaMath | 45 | Jun 5, 2026 |
|---|
| Graph Alignment | Douban | 45 | Jun 23, 2026 |
|---|
| Category Discovery | Food101 | 45 | Apr 14, 2026 |
|---|
| Node Classification Robustness Certification | Texas | 45 | Mar 10, 2026 |
|---|
| Effect estimation on mathematics scores | TIMSS 80% 2019 (train) | 45 | Mar 10, 2026 |
|---|
| Mathematical Reasoning | AIME 2025 | 45 | Jun 9, 2026 |
|---|
| Multi-perspective Alignment | Multi-Perspective Alignment Environment (test) | 45 | Mar 9, 2026 |
|---|
| Radioisotope identification | LaBr3 target-domain sim-to-real (test) | 45 | Mar 9, 2026 |
|---|
| Isotope identification | sim-to-sim (HPGe) target-domain (test) | 45 | Mar 9, 2026 |
|---|
| Radioisotope Identification | NaI(Tl) sim-to-real target-domain (test) | 45 | Mar 9, 2026 |
|---|
| Distribution Estimation | Income | 45 | Mar 6, 2026 |
|---|