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 |
|---|---|---|---|---|
| Steering Validation | 2 | 1 | Apr 10, 2026 | |
| Memory Updating | 2 | 3 | Jun 25, 2026 | |
| LLM Serving Efficiency | 2 | 1 | Apr 10, 2026 | |
| Enterprise interface interaction | 2 | 1 | Apr 10, 2026 | |
| Critique | 2 | 2 | May 15, 2026 | |
| Enterprise interface task completion | 2 | 1 | Apr 10, 2026 | |
| Rule-of-Thumb Generation | 2 | 1 | Feb 18, 2026 | |
| Hallucination self-detection | 2 | 3 | May 1, 2026 | |
| Binary Question Answering |
| 2 |
| 2 |
| Jul 7, 2026 |
| Relational Hallucination Evaluation | 2 | 1 | Apr 10, 2026 |
|---|
| Knowledge-to-action question answering | 2 | 1 | Apr 10, 2026 |
|---|
| Sales interaction performance | 2 | 1 | Apr 10, 2026 |
|---|
| Robot Failure Analysis (MCQ) | 2 | 1 | Apr 10, 2026 |
|---|
| Conversational Behavior Reasoning | 2 | 1 | Feb 19, 2026 |
|---|
| Reasoning Fidelity | 2 | 1 | Apr 14, 2026 |
|---|
| Free-language reasoning | 2 | 1 | Apr 10, 2026 |
|---|
| Graduate-level Q&A | 2 | 2 | Apr 30, 2026 |
|---|
| Language Compositionality | 2 | 2 | Feb 18, 2026 |
|---|
| Faithfulness Hallucination Detection | 2 | 1 | Feb 19, 2026 |
|---|
| Full-duplex Interaction | 2 | 2 | Feb 21, 2026 |
|---|
| Agreement with process human labels | 2 | 1 | Apr 9, 2026 |
|---|
| Self-doubt detection | 2 | 1 | Apr 9, 2026 |
|---|
| Agreement with outcome human labels | 2 | 1 | Apr 9, 2026 |
|---|
| Evaluation Awareness Detection | 2 | 1 | Feb 19, 2026 |
|---|
| General Agent Capability | 2 | 2 | Apr 16, 2026 |
|---|