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 |
|---|---|---|---|---|---|
| Node Classification | Cora 5-shot | 32 | Jun 11, 2026 | ||
| Calibration | TruthfulQA | 32 | Jun 11, 2026 | ||
| Criticism prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 | ||
| Overinclude prediction | Parent data segment-level (5-fold cross-validation) | 32 | Apr 21, 2026 | ||
| Rumination prediction | Parent data segment-level (5-fold cross-validation) |
| 32 |
| Apr 21, 2026 |
| Cohesion prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 |
|---|
| Neutral state prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 |
|---|
| Sadness prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 |
|---|
| Joy prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 |
|---|
| Fear prediction | Parent data segment-level (5-fold cross-validation) | 32 | Apr 21, 2026 |
|---|
| Anger prediction | Parent data segment-level (5-fold cross-validation) | 32 | Apr 21, 2026 |
|---|
| Sentiment prediction | Parent data segment-level (5-fold cross-validation) | 32 | Apr 21, 2026 |
|---|
| Objective trait prediction | Parent data segment-level 5-fold cross-validation | 32 | Apr 21, 2026 |
|---|
| segment-level prediction | offspring 5-fold (val) | 32 | Apr 21, 2026 |
|---|
| Safety and Helpfulness Evaluation | VLGuard | 32 | Jun 4, 2026 |
|---|
| Safety and Helpfulness Evaluation | SPA-VL | 32 | Jun 4, 2026 |
|---|
| Sycophancy Evaluation | Sycophancy Evaluation Dataset | 32 | Apr 21, 2026 |
|---|
| Sycophancy Assessment | BASIL 1.0 (Under-Update) | 32 | Apr 21, 2026 |
|---|
| Sycophancy Assessment | BASIL Over-Update 1.0 | 32 | Apr 21, 2026 |
|---|
| Sycophancy Assessment | BASIL 1.0 (All) | 32 | Apr 21, 2026 |
|---|
| 3D Object Detection | SUN RGB-D | 32 | Apr 20, 2026 |
|---|
| Question Answering | Sciq | 32 | Apr 20, 2026 |
|---|
| Pose Estimation | 7-Scenes | 32 | Apr 16, 2026 |
|---|
| Mathematical Reasoning | AIME25 | 32 | Apr 30, 2026 |
|---|
| Mathematical Reasoning | MATH | 32 | Apr 16, 2026 |
|---|