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 |
|---|---|---|---|---|
| Multi-step reasoning and knowledge retrieval | 2 | 1 | Apr 14, 2026 | |
| Length Extrapolation | 2 | 2 | May 29, 2026 | |
| Proactive information probing | 2 | 1 | Apr 14, 2026 | |
| Rationale alignment | 2 | 2 | Jun 5, 2026 | |
| Generative tasks | 2 | 2 | Apr 24, 2026 | |
| Open-ended arithmetic reasoning | 2 | 1 | Apr 14, 2026 | |
| Arabic Cultural Value Alignment | 2 | 1 | Feb 18, 2026 | |
| Price Negotiation | 2 | 1 | Apr 14, 2026 | |
| Social Intelligence Reasoning |
| 2 |
| 2 |
| Jun 11, 2026 |
| Corrective Instruction Generation | 2 | 1 | Feb 18, 2026 |
|---|
| Skill Invocation Safety Auditing | 2 | 1 | Apr 14, 2026 |
|---|
| Multi-turn Jailbreak Evaluation | 2 | 1 | Apr 14, 2026 |
|---|
| Grade-school reasoning | 2 | 2 | Jun 30, 2026 |
|---|
| Real-trace replay validation | 2 | 1 | Apr 14, 2026 |
|---|
| Math Word Problem Preference | 2 | 1 | Apr 14, 2026 |
|---|
| Broad Knowledge Question Answering | 2 | 1 | Apr 14, 2026 |
|---|
| Logical Reasoning and Reading Comprehension | 2 | 1 | Apr 14, 2026 |
|---|
| Response Harmfulness Classification | 2 | 4 | May 29, 2026 |
|---|
| Loop Suppression | 2 | 1 | Apr 14, 2026 |
|---|
| Aggregate Reasoning Evaluation | 2 | 2 | May 26, 2026 |
|---|
| User Preference | 2 | 2 | Jul 2, 2026 |
|---|
| Context Traceback | 2 | 1 | Apr 14, 2026 |
|---|
| Rule Following | 2 | 1 | Apr 13, 2026 |
|---|
| Language-conditioned simulation | 2 | 1 | Apr 14, 2026 |
|---|
| Long-context Multi-modal Understanding | 2 | 2 | May 14, 2026 |
|---|