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 |
|---|---|---|---|---|
| Conversational Memory Question Answering | 1 | 1 | May 14, 2026 | |
| Automated Interpretability Evaluation | 1 | 2 | Jun 15, 2026 | |
| Commonsense Reasoning and Short-Context Language Understanding | 1 | 1 | May 14, 2026 | |
| Multidisciplinary knowledge and reasoning | 1 | 1 | Mar 5, 2026 | |
| Encoding Speed | 1 | 1 | May 14, 2026 | |
| Hallucination Suppression | 1 | 1 | Feb 18, 2026 | |
| Multi-hop Multiple-choice Question Answering | 1 | 1 | Mar 5, 2026 | |
| Refusal Ablation | 1 | 1 |
| Mar 5, 2026 |
| Psychological Assessment Game Generation Evaluation | 1 | 1 | Feb 18, 2026 |
|---|
| Steering Success Rate | 1 | 1 | Mar 6, 2026 |
|---|
| Helpful Assistant | 1 | 1 | May 15, 2026 |
|---|
| Maritime Dialogue Generation | 1 | 1 | Mar 6, 2026 |
|---|
| Commonsense Reasoning and Question Answering | 1 | 1 | May 15, 2026 |
|---|
| Prompt-to-prompt semantic composition | 1 | 1 | May 15, 2026 |
|---|
| Instruction Following and Tool Use | 1 | 1 | May 15, 2026 |
|---|
| Long-Term Credit Assignment | 1 | 1 | May 15, 2026 |
|---|
| Ranking LLM solutions | 1 | 1 | Feb 18, 2026 |
|---|
| Sequential Reasoning | 1 | 1 | May 15, 2026 |
|---|
| Social dilemma resolution | 1 | 1 | May 15, 2026 |
|---|
| mathematical reasoning via verifiable subquestions | 1 | 1 | Feb 18, 2026 |
|---|
| Human Ranking of Explanation Quality | 1 | 1 | Mar 6, 2026 |
|---|
| Open-ended generative Question Answering | 1 | 1 | May 15, 2026 |
|---|
| Time to First Token | 1 | 1 | Mar 6, 2026 |
|---|
| Trade Negotiation | 1 | 1 | May 15, 2026 |
|---|
| research-level mathematical reasoning | 1 | 1 | Feb 18, 2026 |
|---|