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 |
|---|---|---|---|---|
| Reasoning Token Induction | 1 | 1 | Feb 19, 2026 | |
| General Capability Harmlessness | 1 | 1 | Feb 19, 2026 | |
| Safety Decision Making | 1 | 1 | Apr 8, 2026 | |
| Multimodal Chain-of-Thought Reasoning | 1 | 2 | Jun 9, 2026 | |
| Functionally equivalent reasoning | 1 | 1 | Apr 8, 2026 | |
| Over-refusal rate analysis | 1 | 2 | Apr 21, 2026 | |
| Multi-step dependency reasoning | 1 | 1 | Apr 8, 2026 | |
| Low-level Instruction Generation |
| 1 |
| 1 |
| Apr 8, 2026 |
| Open-ended stress reasoning | 1 | 1 | Apr 8, 2026 |
|---|
| Multi-turn Question Answering | 1 | 1 | Apr 8, 2026 |
|---|
| Rule Alignment Evaluation | 1 | 1 | Feb 18, 2026 |
|---|
| Temporal Reasoning (date) | 1 | 1 | Apr 8, 2026 |
|---|
| Targeted Answer | 1 | 1 | Feb 19, 2026 |
|---|
| Temporal Reasoning (date_season) | 1 | 1 | Apr 8, 2026 |
|---|
| Temporal Reasoning (duration) | 1 | 1 | Apr 8, 2026 |
|---|
| Multi-modal Chain-of-Thought Reasoning | 1 | 1 | Apr 8, 2026 |
|---|
| Multi-turn Jailbreaking Attack | 1 | 1 | Feb 19, 2026 |
|---|
| General Multimodal Perception and Reasoning | 1 | 1 | Apr 8, 2026 |
|---|
| Token Efficiency Evaluation | 1 | 1 | Apr 8, 2026 |
|---|
| LLM data comprehension | 1 | 1 | Apr 8, 2026 |
|---|
| Educational Dialogue Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Quantitative evaluation of LLM feedback against human gold standards | 1 | 1 | Feb 19, 2026 |
|---|
| Emotion Reasoning (ER) | 1 | 1 | Apr 8, 2026 |
|---|
| Over-Refusal Attack Resistance Evaluation | 1 | 1 | Feb 19, 2026 |
|---|
| Emotion-Guided Content Generation (EGCG) | 1 | 1 | Apr 8, 2026 |
|---|