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 |
|---|---|---|---|---|---|
| Metal Artifact Restoration | SynDeepLesion Tiny size (test) | 36 | Apr 9, 2026 | ||
| Metal Artifact Restoration | SynDeepLesion Small size (test) | 36 | Apr 9, 2026 | ||
| Motion Prediction | nuScenes (val) | 36 | Jul 7, 2026 | ||
| Grasping | ManiSkill Simulation YCB objects (test) | 36 | Apr 7, 2026 | ||
| MCD |
| 36 |
| Apr 7, 2026 |
| Video understanding | Aggregated Average Score | 36 | May 12, 2026 |
|---|
| Personality Assessment | BFI Self-report 44-item (test) | 36 | Apr 7, 2026 |
|---|
| Mathematical Reasoning | MGSM Rev2 | 36 | Jun 23, 2026 |
|---|
| Scientific Reasoning | GPQA Diamond | 36 | Apr 6, 2026 |
|---|
| Mathematical Reasoning | GSM8K | 36 | Apr 6, 2026 |
|---|
| Mathematical Reasoning | AIME 25 | 36 | Apr 6, 2026 |
|---|
| Mathematical Reasoning | AIME24 | 36 | Apr 6, 2026 |
|---|
| Target-View Object Description | ViewBench Object | 36 | Apr 6, 2026 |
|---|
| Causal Graph Discovery | Child 20 nodes, 25 edges | 36 | Apr 6, 2026 |
|---|
| Mathematical Reasoning | OlympiadBench | 36 | May 11, 2026 |
|---|
| ECG Classification | CPSC 2018 | 36 | Jun 23, 2026 |
|---|
| Jailbreak Defense | MultiJail | 36 | Apr 3, 2026 |
|---|
| Misinformation Correction | MisinfoCorrect | 36 | Apr 3, 2026 |
|---|
| Counterspeech Generation | CheckCovid (cross generalization) | 36 | Apr 3, 2026 |
|---|
| Image Captioning | MS COCO | 36 | Apr 2, 2026 |
|---|
| Multi-hop Question Answering | MuSiQue (test) | 36 | Apr 2, 2026 |
|---|
| Chatbot workload | ShareGPT | 36 | Apr 2, 2026 |
|---|
| Code generation | MBPP+ | 36 | Jul 7, 2026 |
|---|
| Mathematical Reasoning | AIME 2023 | 36 | May 13, 2026 |
|---|
| Medical Reasoning | DDXPlus | 36 | May 18, 2026 |
|---|