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 |
|---|---|---|---|---|
| Generation Enhances Understanding | 1 | 1 | May 13, 2026 | |
| Collective Reasoning | 1 | 1 | May 14, 2026 | |
| Factual Evaluation | 1 | 1 | Mar 5, 2026 | |
| Safety Constraint Recall Evaluation | 1 | 1 | May 14, 2026 | |
| Hypothetical Instruction-Based Image Editing | 1 | 1 | May 14, 2026 | |
| Human Pairwise Preference Evaluation | 1 | 1 | Mar 5, 2026 | |
| Long-horizon language-conditioned manipulation | 1 | 3 | Jun 4, 2026 | |
| Physician evaluation of long-form medical answers |
| 1 |
| 1 |
| Feb 18, 2026 |
| Logic Puzzles | 1 | 1 | May 14, 2026 |
|---|
| Unified Multi-task Language Understanding and Instruction Following | 1 | 2 | Jun 5, 2026 |
|---|
| Response Alignment | 1 | 1 | Mar 5, 2026 |
|---|
| Chess Reasoning Quality Evaluation | 1 | 1 | May 14, 2026 |
|---|
| Hallucination / grounding | 1 | 1 | May 14, 2026 |
|---|
| General reasoning / multi-discipline | 1 | 2 | May 20, 2026 |
|---|
| Factual Grounding | 1 | 1 | May 14, 2026 |
|---|
| Commonsense Reasoning and Knowledge Question Answering | 1 | 1 | Feb 27, 2026 |
|---|
| Response Generation Quality | 1 | 1 | Mar 5, 2026 |
|---|
| Conversational Alignment | 1 | 1 | May 14, 2026 |
|---|
| Comparative Ranking | 1 | 1 | Feb 27, 2026 |
|---|
| Intent Reflection | 1 | 1 | Mar 5, 2026 |
|---|
| Subjective evaluation of agent feedback | 1 | 1 | May 14, 2026 |
|---|
| Sponsored product promotion | 1 | 1 | May 14, 2026 |
|---|
| Long-term Question Answering | 1 | 1 | Mar 5, 2026 |
|---|
| Adversarial Hallucination Attack | 1 | 1 | May 14, 2026 |
|---|
| Open-ended MCQA | 1 | 1 | May 14, 2026 |
|---|