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 |
|---|---|---|---|---|---|
| Out-of-Distribution Detection | CIFAR-10 (test) | 35 | May 19, 2026 | ||
| Math Word Problems | SVAMP | 35 | Jun 19, 2026 | ||
| Multimodal Perception | MME P | 35 | Jun 19, 2026 | ||
| Infrared Small Target Detection | SIRST3 Camouflaged partition | 35 | May 15, 2026 | ||
| Infrared Small Target Detection | SIRST3 Faint partition |
| 35 |
| May 15, 2026 |
| Infrared Small Target Detection | SIRST3 Filamentary partition | 35 | May 15, 2026 |
|---|
| Infrared Small Target Detection | SIRST3 Salient partition | 35 | May 15, 2026 |
|---|
| Camera Pose Estimation | Sintel dataset | 35 | May 22, 2026 |
|---|
| Robot Manipulation | RobotTwin Clean v1 (test) | 35 | May 14, 2026 |
|---|
| Knowledge-intensive reasoning | SuperGPQA | 35 | Jul 2, 2026 |
|---|
| Object Hallucination Detection | POPE average over three sampling strategies | 35 | May 13, 2026 |
|---|
| Object Hallucination Detection | CLEVR | 35 | May 13, 2026 |
|---|
| Multiple Exposure Correction | MSEC Over 1 (test) | 35 | May 27, 2026 |
|---|
| Multiple Exposure Correction | MSEC Under 1 (test) | 35 | May 27, 2026 |
|---|
| General Reasoning | GPQA-Diamond & MMLU-Pro | 35 | May 13, 2026 |
|---|
| PI reconstruction | Anatomical T1 contrast out-of-distribution | 35 | May 12, 2026 |
|---|
| Parallel Imaging Reconstruction | CORPDFS | 35 | May 12, 2026 |
|---|
| Parallel Imaging Reconstruction | knee dataset CORPD-weighted in-distribution (test) | 35 | May 12, 2026 |
|---|
| Traitor win probability estimation | The Traitors Game Televised range configurations 15 <= n <= 25 Migdał value based | 35 | May 12, 2026 |
|---|
| Node Classification | Yelp | 35 | Jun 2, 2026 |
|---|
| 3D Multi-Tote Handling | 3D Rack-Climbing Robotic Systems (Exotec) Extended Large-Scale Instances | 35 | May 12, 2026 |
|---|
| SOC prediction | Average (FTP-75 and PDMHC) | 35 | May 12, 2026 |
|---|
| SOC prediction | PDMHC | 35 | May 12, 2026 |
|---|
| SOC prediction | FTP-75 | 35 | May 12, 2026 |
|---|
| Fairness-aware Classification | Dutch | 35 | Jun 11, 2026 |
|---|