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 |
|---|---|---|---|---|
| Output Diversity | 4 | 4 | Jun 1, 2026 | |
| Dialogue turn-taking | 4 | 1 | Apr 21, 2026 | |
| Insight Discovery and Guidance | 4 | 1 | Apr 21, 2026 | |
| Steerability Correlation Analysis | 4 | 1 | Apr 20, 2026 | |
| Response-level Hallucination Detection | 4 | 2 | Jul 7, 2026 | |
| Emergent Misalignment Measurement | 4 | 1 | Mar 6, 2026 | |
| Pairwise Human Preference Prediction | 4 | 2 | May 6, 2026 | |
| Jailbreak Transferability | 4 | 1 | Mar 4, 2026 | |
| 4 |
| 1 |
| Mar 4, 2026 |
| Personality Understanding | 4 | 2 | May 8, 2026 |
|---|
| LLM-as-judge head-to-head comparison | 4 | 1 | Mar 4, 2026 |
|---|
| False Refusal Evaluation | 4 | 2 | Mar 17, 2026 |
|---|
| Personality Alignment | 4 | 2 | May 1, 2026 |
|---|
| Multilingual Reasoning and Language Understanding | 4 | 1 | Apr 15, 2026 |
|---|
| Reasoning-Aware Threat Detection | 4 | 1 | Mar 4, 2026 |
|---|
| Quantitative Reasoning | 4 | 3 | Jun 2, 2026 |
|---|
| Multi-step LLM Interaction | 4 | 1 | Feb 18, 2026 |
|---|
| Tool-use behavioral profiling | 4 | 1 | Apr 15, 2026 |
|---|
| Global Question Answering | 4 | 1 | Apr 21, 2026 |
|---|
| Long-context recall | 4 | 2 | Jun 30, 2026 |
|---|
| Chat & Instruction Following | 4 | 2 | Jul 7, 2026 |
|---|
| Open-ended evaluation | 4 | 4 | Jul 8, 2026 |
|---|
| Instruction Generalization | 4 | 2 | Apr 28, 2026 |
|---|
| Scientific and General Reasoning | 4 | 3 | Feb 24, 2026 |
|---|
| Conversational Semantic Parsing | 4 | 2 | Feb 18, 2026 |
|---|