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 |
|---|---|---|---|---|---|
| Creative Writing | Creative Writing Evaluation Set 1.0 (test) | 54 | May 12, 2026 | ||
| Commonsense Reasoning | Commonsense Reasoning | 54 | Jun 9, 2026 | ||
| Image Classification | CIFAR-100 (test) | 54 | May 11, 2026 | ||
| Mathematical Reasoning Calibration | AIME 24-25 | 54 | May 11, 2026 | ||
| Mathematical Reasoning Calibration |
|---|
| MATH 500 |
| 54 |
| May 11, 2026 |
| Token Amplification Attack | Empirical Study Tasks 60 reasoning tasks 1.0 (test) | 54 | May 8, 2026 |
|---|
| Deepfake Detection | WDF | 54 | May 11, 2026 |
|---|
| Tabular Classification | 253 Tabular Datasets | 54 | May 7, 2026 |
|---|
| Medical diagnostic value preservation | NHANES 2017-2018 (test) | 54 | May 6, 2026 |
|---|
| WSI Classification | TCGA-IDH | 54 | May 4, 2026 |
|---|
| Question Answering | ClimaQA | 54 | Apr 30, 2026 |
|---|
| Math Reasoning | GSM8K | 54 | Apr 29, 2026 |
|---|
| Multi-camera Pose Optimization | Synthetic Dataset | 54 | Apr 28, 2026 |
|---|
| Object Detection | Pascal VOC | 54 | Apr 28, 2026 |
|---|
| Image Classification | ImageNet-C | 54 | Jul 1, 2026 |
|---|
| CTR prediction | m4a | 54 | Apr 24, 2026 |
|---|
| Simulation-based Inference | Hierarchical SLCP | 54 | Apr 23, 2026 |
|---|
| Continuum Field Reconstruction (Rollout) | 2D Navier-Stokes nu=1e-3 | 54 | Apr 23, 2026 |
|---|
| Task-incremental learning | Tiny-ImageNet 20 tasks | 54 | May 18, 2026 |
|---|
| Leakage Analysis in LLM-based Tutoring | GSM8K | 54 | Apr 23, 2026 |
|---|
| Average treatment effect estimation | Synthetic Data | 54 | Apr 21, 2026 |
|---|
| Multi-task Question Answering | ARC, OBQA, and Riddle Combined (test) | 54 | Apr 21, 2026 |
|---|
| Safety Evaluation | MEMEVOBENCH Workflow Style 1.0 (test) | 54 | Apr 20, 2026 |
|---|
| Safety Evaluation | MEMEVOBENCH QA Style 1.0 (test) | 54 | Apr 20, 2026 |
|---|
| Zero-shot Reasoning | Zero-Shot Reasoning Tasks (ARC-C, ARC-E, BoolQ, Hella, OBQA, PIQA, SIQA, Wino) | 54 | Apr 16, 2026 |
|---|