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 |
|---|---|---|---|---|
| General Knowledge and Reasoning | 5 | 8 | Jun 29, 2026 | |
| In-context Generation | 5 | 1 | Apr 23, 2026 | |
| Proactive dialogue | 5 | 3 | Jun 15, 2026 | |
| Comprehension Questions | 5 | 1 | Apr 21, 2026 | |
| Personality Steering | 5 | 3 | May 8, 2026 | |
| Over-refusal Compliance | 5 | 1 | Mar 5, 2026 | |
| Tool Invocation Refusal | 5 | 1 | Apr 14, 2026 | |
| Preference Alignment Evaluation | 5 | 5 | Jun 4, 2026 | |
| Personalized VLM Alignment |
| 5 |
| 1 |
| Feb 18, 2026 |
| Personalized response selection | 5 | 1 | Feb 18, 2026 |
|---|
| Legal Contract Revision | 5 | 1 | Apr 14, 2026 |
|---|
| Sequential Composition Generalization | 5 | 1 | Apr 14, 2026 |
|---|
| Lifelong Model Editing | 5 | 2 | May 13, 2026 |
|---|
| Prosocial Alignment | 5 | 1 | Feb 19, 2026 |
|---|
| Language Reasoning | 5 | 7 | Jun 19, 2026 |
|---|
| Multi-turn Inference Latency | 5 | 1 | Apr 10, 2026 |
|---|
| Reward alignment | 5 | 3 | Jul 7, 2026 |
|---|
| Task Vector Performance | 5 | 1 | Apr 13, 2026 |
|---|
| Memory Question Answering | 5 | 3 | Jun 18, 2026 |
|---|
| Hallucination Rate Assessment | 5 | 1 | Apr 13, 2026 |
|---|
| Diagnostic Reasoning | 5 | 4 | Jun 8, 2026 |
|---|
| Multi-agent Debate | 5 | 2 | Jun 18, 2026 |
|---|
| Preference Assessment | 5 | 1 | Jun 29, 2026 |
|---|
| Human-Metric Correlation | 5 | 1 | Feb 19, 2026 |
|---|
| Process-level Evaluation | 5 | 1 | Apr 14, 2026 |
|---|