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 |
|---|---|---|---|---|---|
| Language Modeling | WikiText | 47 | Jul 7, 2026 | ||
| Lemma Discovery | Octonions | 47 | Jun 4, 2026 | ||
| Question Answering | HotpotQA | 47 | Jun 2, 2026 | ||
| Question Answering | HotpotQA | 47 | Jun 2, 2026 | ||
| Visual Reasoning | CV-Bench | 47 | Jul 7, 2026 | ||
| Text-to-Image Retrieval | MSCOCO |
| 47 |
| Jun 2, 2026 |
| PDE Solving | Navier-Stokes | 47 | Jun 30, 2026 |
|---|
| Role-playing | CharacterBench latest (full) | 47 | May 26, 2026 |
|---|
| Science Question Answering | GPQA Diamond | 47 | Jun 5, 2026 |
|---|
| Image Classification | CIFAR-10 | 47 | Jul 2, 2026 |
|---|
| Action Recognition | Epic-Kitchens | 47 | Jun 2, 2026 |
|---|
| Visual Question Answering for object probing | POPE Aggregated random, popular, and adversarial | 47 | May 20, 2026 |
|---|
| Planning | PlanBench | 47 | Jun 9, 2026 |
|---|
| Mathematical Reasoning | HMMT | 47 | Jun 9, 2026 |
|---|
| Mathematical Reasoning | GSM8K (test) | 47 | May 13, 2026 |
|---|
| Multiple Choice Classification | MMLU | 47 | Jun 2, 2026 |
|---|
| Class-incremental image classification | TinyImageNet | 47 | Jun 5, 2026 |
|---|
| Image Classification | Spawrious M2M-Hard | 47 | Jun 4, 2026 |
|---|
| Image Classification | Spawrious O2O-Hard | 47 | Jun 4, 2026 |
|---|
| Mathematical Reasoning | Olympiad | 47 | May 28, 2026 |
|---|
| Online Continual Test-time Adaptation | ImageNet-C Severity 5 (test) | 47 | May 20, 2026 |
|---|
| Drug-target binding affinity prediction | PDBbind Core Set v2016 | 47 | Jun 15, 2026 |
|---|
| Harmfulness Detection | WildGuard | 47 | Jun 1, 2026 |
|---|
| Text-to-Image Person Retrieval | CUHK-PEDES | 47 | Jun 30, 2026 |
|---|
| Early Action Prediction | SSsub21 | 47 | Apr 21, 2026 |
|---|