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 |
|---|---|---|---|---|
| Process-level verification | 4 | 1 | Feb 18, 2026 | |
| Multilingual Reasoning and Language Understanding | 4 | 1 | Apr 15, 2026 | |
| Copying Task | 4 | 2 | May 12, 2026 | |
| Tool-use behavioral profiling | 4 | 1 | Apr 15, 2026 | |
| Chat & Instruction Following | 4 | 2 | Jul 7, 2026 | |
| Reasoning-Aware Threat Detection | 4 | 1 | Mar 4, 2026 | |
| Transitive reasoning | 4 | 1 | Apr 15, 2026 | |
| End-to-end task-oriented dialogue | 4 | 13 | Jun 9, 2026 | |
| Long-Horizon Stability |
| 4 |
| 2 |
| May 14, 2026 |
| Utility assessment | 4 | 4 | Apr 20, 2026 |
|---|
| Explanation self-consistency | 4 | 1 | Apr 14, 2026 |
|---|
| Therapeutic Game Evaluation | 4 | 1 | Apr 14, 2026 |
|---|
| Single-turn Dialogue | 4 | 3 | May 4, 2026 |
|---|
| Pairwise Evaluation | 4 | 2 | Jun 1, 2026 |
|---|
| Function Vector Evaluation | 4 | 1 | Feb 27, 2026 |
|---|
| Comprehensive Examination | 4 | 4 | May 19, 2026 |
|---|
| CoT Soundness Evaluation | 4 | 1 | Apr 10, 2026 |
|---|
| CoT Naturalness | 4 | 1 | Apr 10, 2026 |
|---|
| Multi-party Dialogue Generation | 4 | 1 | Apr 10, 2026 |
|---|
| Input-based feature description evaluation | 4 | 1 | Feb 18, 2026 |
|---|
| Output-based feature description evaluation | 4 | 1 | Feb 18, 2026 |
|---|
| Information Analysis and Processing | 4 | 1 | Apr 8, 2026 |
|---|
| Knowledge Distillation Robustness | 4 | 1 | Apr 8, 2026 |
|---|
| Output Diversity | 4 | 4 | Jun 1, 2026 |
|---|
| Disruption | 4 | 1 | Apr 10, 2026 |
|---|