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 |
|---|---|---|---|---|---|
| Hallucination Detection | MT | 64 | Jun 18, 2026 | ||
| Hallucination Detection | Summ | 64 | Jun 18, 2026 | ||
| Hallucination Detection | QA | 64 | Jun 18, 2026 | ||
| Mathematical Reasoning | GSM-Hard | 64 | Jun 30, 2026 | ||
| Jailbreak | AdvBench (Intra-episode) | 64 | Jun 11, 2026 |
| Image Classification | TinyImageNet Fourth Session Transition | 64 | Jun 9, 2026 |
|---|
| Mathematical Reasoning | DART-Math DM-5 | 64 | Jun 8, 2026 |
|---|
| Mathematical Reasoning | DART-Math DM-4 | 64 | Jun 8, 2026 |
|---|
| Mathematical Reasoning | DART-Math DM-3 | 64 | Jun 8, 2026 |
|---|
| Mathematical Reasoning | DART-Math DM-2 | 64 | Jun 8, 2026 |
|---|
| Language Modeling | WikiText-2 | 64 | Jun 23, 2026 |
|---|
| Membership Privacy Estimation | CiteSeer 50% nodes sampled | 64 | Jun 4, 2026 |
|---|
| Privacy parameter estimation | CiteSeer 25% nodes sampled (train) | 64 | Jun 4, 2026 |
|---|
| Membership Inference Attack | Cora 25% nodes (train) | 64 | Jun 4, 2026 |
|---|
| Node Classification | Cora (test) | 64 | Jul 1, 2026 |
|---|
| Graph Explanation Fidelity | MAG | 64 | Jun 4, 2026 |
|---|
| Heuristic Search | Blind heuristic benchmark set | 64 | Jun 2, 2026 |
|---|
| 3D Gaussian Splatting Rendering | Mip-NeRF 360 4K 1.0 | 64 | Jun 2, 2026 |
|---|
| 3D Gaussian Splatting Rendering | Mip-NeRF 360 1080p 1.0 | 64 | Jun 2, 2026 |
|---|
| Image Classification | CIFAR10 | 64 | May 28, 2026 |
|---|
| Image Classification | CIFAR100 | 64 | May 28, 2026 |
|---|
| Image Classification | TinyImageNet | 64 | May 28, 2026 |
|---|
| Safety Classification | AUTALIC (test) | 64 | May 27, 2026 |
|---|
| Speech Recognition | EABI | 64 | May 26, 2026 |
|---|
| Offline Reinforcement Learning | MuJoCo Hopper | 64 | May 26, 2026 |
|---|