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 |
|---|---|---|---|---|---|
| Text Reconstruction | EMBEDDINGGEMMA 300M | 54 | Jun 18, 2026 | ||
| Bag-level classification | CIFAR-10 (test) | 54 | Jun 11, 2026 | ||
| Noisy-label detection | ImageNet 100 | 54 | Jul 2, 2026 | ||
| Clustering | MultiFashion V=3, K=10 | 54 | Jun 4, 2026 | ||
| Clustering | CUB K=10 v2 | 54 | Jun 4, 2026 | ||
| Object-level Representation | Real Indoor Dataset |
| 54 |
| Jun 4, 2026 |
| Lower Bound Search | Generalized Kissing Number | 54 | Jun 4, 2026 |
|---|
| Refusal suppression | JailbreakBench (test) | 54 | Jun 4, 2026 |
|---|
| Prediction | GEODRIVE-BENCH | 54 | Jun 4, 2026 |
|---|
| Tabular Learning | TabArena | 54 | Jun 2, 2026 |
|---|
| Interactive Instruction Following | ALFWorld Unseen | 54 | Jun 19, 2026 |
|---|
| GS Depth Rendering | TAT Dataset | 54 | Jun 2, 2026 |
|---|
| GS Depth Rendering | DTU Dataset | 54 | Jun 2, 2026 |
|---|
| GS Depth Rendering | Replica Dataset | 54 | Jun 2, 2026 |
|---|
| Regression | Electrical Network Dataset | 54 | Jun 2, 2026 |
|---|
| Neural Network Compression | Polymerization | 54 | Jun 2, 2026 |
|---|
| Prototype Selection | Real-world datasets | 54 | Jun 2, 2026 |
|---|
| Classification | Real-world datasets Aggregate Mean | 54 | Jun 2, 2026 |
|---|
| Prototype Selection | Aggregate of multiple datasets (per-fold instances) | 54 | Jun 2, 2026 |
|---|
| Prototype Selection | Real-world datasets aggregated (test) | 54 | Jun 2, 2026 |
|---|
| Attack Success Rate | DirectHarm4 | 54 | Jun 18, 2026 |
|---|
| Multi-label Bioacoustics | nbp | 54 | Jun 1, 2026 |
|---|
| Multi-label Bioacoustics | uhh | 54 | Jun 1, 2026 |
|---|
| Multi-label Bioacoustics | sne | 54 | Jun 1, 2026 |
|---|
| Multi-label Bioacoustics | nes | 54 | Jun 1, 2026 |
|---|