Loading the SOTA2 catalog…
SOTA2 Research · tasks
Explore the problems researchers are working on and the benchmarks used to measure progress.
| Task Name | Domain | Benchmarks | Papers | Last Update |
|---|---|---|---|---|
| Knowledge Synthesis | 1 | 1 | Apr 13, 2026 | |
| Procedural Logic Reasoning | 1 | 1 | Apr 13, 2026 | |
| Subjective Alignment | 1 | 1 | Feb 18, 2026 | |
| General-Purpose Utility | 1 | 1 | Apr 13, 2026 | |
| Instruction-based Navigation | 1 | 1 | Feb 19, 2026 | |
| Long-horizon Mathematical Reasoning | 1 | 2 | May 29, 2026 | |
| Predictive evidence reasoning | 1 | 1 | Apr 13, 2026 | |
| Editing Alignment Assessment | 1 | 1 | Feb 20, 2026 | |
| Multimodal Reasoning Average |
| 1 |
| 1 |
| Apr 13, 2026 |
| Unintended Attack Detection | 1 | 1 | Apr 13, 2026 |
|---|
| Counterfactual Question Answering | 1 | 1 | Feb 20, 2026 |
|---|
| Overall Preference | 1 | 1 | Apr 13, 2026 |
|---|
| Long-horizon reasoning for robotic manipulation | 1 | 2 | Apr 24, 2026 |
|---|
| Challenging Reasoning Tasks | 1 | 1 | Apr 13, 2026 |
|---|
| General Knowledge Exam | 1 | 1 | Feb 20, 2026 |
|---|
| Ethical and Affective Alignment | 1 | 1 | Apr 13, 2026 |
|---|
| Vision-dependent Multimodal Reasoning | 1 | 2 | Jun 8, 2026 |
|---|
| Personalized Understanding | 1 | 1 | Feb 20, 2026 |
|---|
| Social Deduction Game Agent Evaluation | 1 | 1 | Apr 13, 2026 |
|---|
| Classification with expert deferral | 1 | 1 | Apr 13, 2026 |
|---|
| Factual Correctness | 1 | 1 | Feb 18, 2026 |
|---|
| Personalized Attribute-Reasoning Generation | 1 | 1 | Feb 20, 2026 |
|---|
| Event Logical Reasoning | 1 | 1 | Apr 13, 2026 |
|---|
| Instruction Hierarchy Reasoning | 1 | 1 | Apr 13, 2026 |
|---|
| Computational Reasoning | 1 | 1 | Apr 13, 2026 |
|---|