Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Pathology Image Classification | PanNuke (test) | 37 | Jun 9, 2026 | ||
| Pathology Image Classification | WSSS4LUAD (test) | 37 | Jun 9, 2026 | ||
| Pathology Image Classification | NCT-CRC (test) | 37 | Jun 9, 2026 | ||
| Pathology Image Classification | Osteo (test) | 37 | Jun 9, 2026 | ||
| Pathology Image Classification | LC-COLON (test) |
| 37 |
| Jun 9, 2026 |
| Pathology Image Classification | LC-LUNG (test) | 37 | Jun 9, 2026 |
|---|
| Pathology Image Classification | SKINTUMOR (test) | 37 | Jun 9, 2026 |
|---|
| Pathology Image Classification | SKINCANCER (test) | 37 | Jun 9, 2026 |
|---|
| Pathology Image Classification | SICAP-MIL (test) | 37 | Jun 9, 2026 |
|---|
| Reading Comprehension | BoolQ | 37 | Jun 18, 2026 |
|---|
| Image Classification | CelebA (test) | 37 | Jul 2, 2026 |
|---|
| Multi-label biomedical classification | PubMed (test) | 37 | Jun 2, 2026 |
|---|
| Multi-label biomedical classification | Ohsumed (test) | 37 | Jun 2, 2026 |
|---|
| Complex reasoning | SciFact (test) | 37 | Jun 2, 2026 |
|---|
| Complex reasoning | VitaminC (test) | 37 | Jun 2, 2026 |
|---|
| Complex reasoning | FEVER (test) | 37 | Jun 2, 2026 |
|---|
| High-stakes specialized classification | Claude9 (test) | 37 | Jun 2, 2026 |
|---|
| High-stakes specialized classification | DDI (test) | 37 | Jun 2, 2026 |
|---|
| General classification | AGNews (test) | 37 | Jun 2, 2026 |
|---|
| General Reasoning | Out-of-Distribution Benchmarks MMLU-P, ARC-c, GPQA | 37 | Jun 23, 2026 |
|---|
| Pairwise evaluation | AlpacaEval | 37 | Jun 1, 2026 |
|---|
| In-Context Value Alignment | Value Composition (Overall) | 37 | May 27, 2026 |
|---|
| GUI Web Agent Navigation | Mind2Web Online | 37 | Jun 2, 2026 |
|---|
| Science Question Answering | ResearchQA | 37 | Jun 16, 2026 |
|---|
| Autonomous Driving Planning | NAVSIM v1 (navtest) | 37 | Jul 1, 2026 |
|---|