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 |
|---|---|---|---|---|
| LLM-as-a-Judge Routing | 1 | 1 | May 12, 2026 | |
| Multi-choice reasoning | 1 | 1 | Mar 4, 2026 | |
| Automated Research Efficiency Analysis | 1 | 1 | May 12, 2026 | |
| Ethical alignment evaluation | 1 | 1 | May 12, 2026 | |
| Consulting and Recommendations | 1 | 1 | Feb 18, 2026 | |
| Skill invocation in LLM agents | 1 | 1 | Mar 4, 2026 | |
| Moral preference alignment | 1 | 1 | May 12, 2026 | |
| Per-country Preference Alignment | 1 | 1 | May 12, 2026 | |
| Interactive agentic task completion |
|---|
| 1 |
| 2 |
| Jun 4, 2026 |
| Cascading Dialogue Success | 1 | 1 | Feb 18, 2026 |
|---|
| Few-shot (5-shot) performance | 1 | 1 | Feb 18, 2026 |
|---|
| Behavior Steering | 1 | 1 | Feb 19, 2026 |
|---|
| Selective Copy | 1 | 1 | Mar 4, 2026 |
|---|
| Truthfulness and Calibration Evaluation | 1 | 1 | May 12, 2026 |
|---|
| Behavior Error Detection | 1 | 1 | May 12, 2026 |
|---|
| Behavior Question Answering | 1 | 1 | May 12, 2026 |
|---|
| Random-generation diversity evaluation | 1 | 1 | May 13, 2026 |
|---|
| Drafting legal advice letters | 1 | 1 | May 13, 2026 |
|---|
| Alignment and Safety Evaluation | 1 | 1 | May 13, 2026 |
|---|
| Memory Transfer Continuity | 1 | 1 | May 13, 2026 |
|---|
| Generation scoring | 1 | 1 | Feb 18, 2026 |
|---|
| Negotiation task (Sell&Buy) | 1 | 1 | Mar 4, 2026 |
|---|
| Long-horizon web tasks | 1 | 1 | May 13, 2026 |
|---|
| Shopping Planning | 1 | 1 | May 13, 2026 |
|---|
| Negotiation task (Ultimatum) | 1 | 1 | Mar 4, 2026 |
|---|