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 |
|---|---|---|---|---|---|
| Kernel Ridge Regression | CENSUS (test) | 35 | Jun 5, 2026 | ||
| Audio Classification | UrbanSound8K single-label | 35 | Jun 4, 2026 | ||
| Sparse Logistic Regression | ARCENE (test) | 35 | Jun 4, 2026 | ||
| Mathematical Reasoning | AIME 24 | 35 | Jun 30, 2026 | ||
| Mathematical Reasoning | AIME 25 | 35 | Jun 30, 2026 |
| Speech Understanding | MMSU | 35 | Jul 9, 2026 |
|---|
| Text-based Visual Question Answering | TextVQA | 35 | Jul 3, 2026 |
|---|
| Sequential Recommendation | Toys | 35 | Jun 18, 2026 |
|---|
| Sequential Recommendation | Sports | 35 | Jun 18, 2026 |
|---|
| Safety Evaluation | SORRY-Bench | 35 | Jun 2, 2026 |
|---|
| Multiple-Choice Questioning | SafetyBench English (test) | 35 | Jun 2, 2026 |
|---|
| Truthfulness Evaluation | TruthfulQA | 35 | Jun 2, 2026 |
|---|
| Regression | Energy Consumption | 35 | Jun 2, 2026 |
|---|
| Regression | Housing Prices | 35 | Jun 2, 2026 |
|---|
| Aspect Sentiment Triplet Extraction | Rest 2016 (test) | 35 | Jun 1, 2026 |
|---|
| Aspect Sentiment Triplet Extraction | Rest 2014 (test) | 35 | Jun 1, 2026 |
|---|
| Knowledge-intensive Claim Extraction and Information Retrieval | 75-case (test) | 35 | Jun 1, 2026 |
|---|
| Value Structure Alignment | Portrait Values Questionnaire (PVQ) | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench OOD v2 | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench v2 (test) | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench v2 (val) | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench OOD | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench (test) | 35 | May 29, 2026 |
|---|
| Clinical Task Execution | MedAgentBench (val) | 35 | May 29, 2026 |
|---|
| Image Classification | Aggregate of 9 benchmarks (CIFAR10, CIFAR100, EuroSAT, OxfordPet, Flowers102, Food101, SUN397, DTD, Caltech101) Full-data | 35 | May 28, 2026 |
|---|