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 |
|---|---|---|---|---|
| Disagreement Handling | 1 | 1 | Mar 13, 2026 | |
| Mathematical Reasoning Repair | 1 | 1 | May 26, 2026 | |
| Task-oriented Dialog Response Generation | 1 | 1 | Feb 18, 2026 | |
| Aggregate Benchmark Performance | 1 | 1 | Jun 19, 2026 | |
| Routine Task Management | 1 | 1 | Mar 13, 2026 | |
| Value-action alignment evaluation | 1 | 1 | Feb 19, 2026 | |
| General Task Performance | 1 | 1 | Feb 19, 2026 | |
| Regional knowledge and conversational settings | 1 | 1 | May 26, 2026 | |
| General performance assessment |
|---|
| 1 |
| 1 |
| May 26, 2026 |
| Reward-oriented Decoding | 1 | 1 | Feb 18, 2026 |
|---|
| Human preference evaluation for response quality | 1 | 1 | May 26, 2026 |
|---|
| Single-turn child safety evaluation | 1 | 1 | May 26, 2026 |
|---|
| Multi-turn Refinement | 1 | 1 | Jun 19, 2026 |
|---|
| Belief reasoning | 1 | 1 | Mar 26, 2026 |
|---|
| Dual-reference generation | 1 | 1 | Jun 19, 2026 |
|---|
| Role-play dialogue comprehension | 1 | 1 | May 26, 2026 |
|---|
| Polish Instruction Following | 1 | 1 | Mar 13, 2026 |
|---|
| Multi-discipline Knowledge Evaluation | 1 | 1 | May 26, 2026 |
|---|
| Digit Span | 1 | 1 | May 26, 2026 |
|---|
| Aggregate Cognitive Performance | 1 | 1 | May 26, 2026 |
|---|
| Harmful question-answering | 1 | 1 | Feb 18, 2026 |
|---|
| Memory Construction Quality | 1 | 1 | May 26, 2026 |
|---|
| Trait-wise Automated Essay Scoring | 1 | 1 | May 26, 2026 |
|---|
| Language Model Performance Evaluation | 1 | 1 | May 26, 2026 |
|---|
| Watermarked Text Generation | 1 | 1 | May 26, 2026 |
|---|