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 | PubMed | 59 | May 29, 2026 | ||
| Math Reasoning | MATH (test) | 59 | May 12, 2026 | ||
| Math Reasoning | AIME 2025 | 59 | Jun 9, 2026 | ||
| General Reasoning | GPQA | 59 | May 28, 2026 | ||
| Deep search | gaia |
| 59 |
| May 29, 2026 |
| Mathematical Reasoning | AIME 24 | 59 | Feb 26, 2026 |
|---|
| Temporal Knowledge Graph Reasoning | ICEWS14 (test) | 59 | Feb 26, 2026 |
|---|
| Regression | Elevation | 59 | Jun 19, 2026 |
|---|
| Visual Localization | Cambridge Landmarks | 59 | Jul 3, 2026 |
|---|
| Text-to-Video Retrieval | MSRVTT | 59 | Mar 25, 2026 |
|---|
| Class Incremental Learning | CUB200 10 Tasks | 59 | Mar 13, 2026 |
|---|
| Image Classification | FGVC Aircraft | 59 | Jul 2, 2026 |
|---|
| Mathematical Reasoning | OlympiadBench Math (test) | 59 | Feb 26, 2026 |
|---|
| Denoising | ShapeNet In-Context | 59 | Apr 6, 2026 |
|---|
| Reconstruction | ShapeNet In-Context | 59 | Apr 6, 2026 |
|---|
| Logic reasoning | Tracking Shuffled Objects BBH | 59 | May 20, 2026 |
|---|
| Image Classification | CIFAR-10 Dir(0.5) | 59 | May 25, 2026 |
|---|
| OOD Detection | ImageNet-1k ID Places OOD | 59 | Mar 26, 2026 |
|---|
| OOD Detection | ImageNet-1k ID iNaturalist OOD | 59 | May 26, 2026 |
|---|
| LLM-as-a-Judge | PreferenceBench | 59 | Apr 23, 2026 |
|---|
| Mathematical Reasoning | MATH (val) | 59 | May 18, 2026 |
|---|
| Temporal Question Grounding | NExT-GQA | 59 | Mar 31, 2026 |
|---|
| Multimodal Reasoning | SEED-BENCH | 59 | Jul 7, 2026 |
|---|
| Dynamic Facial Expression Recognition | FERV39k | 59 | Jul 1, 2026 |
|---|
| Referring Video Object Segmentation | Ref-DAVIS | 59 | May 20, 2026 |
|---|