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 |
|---|---|---|---|---|---|
| Multi-Depot Vehicle Routing Problem | INCOM MDVRP SCAIL 2024 | 32 | Feb 26, 2026 | ||
| Audio Time-Stretching | Audio Excerpts 4x stretch | 32 | Feb 26, 2026 | ||
| Audio Time-Stretching | Audio Excerpts 2x stretch | 32 | Feb 26, 2026 | ||
| Mean Estimation under MNAR | USS (test) | 32 | Feb 26, 2026 | ||
| Tabular Classification | Diabetes (test) | 32 | Apr 28, 2026 | ||
| Instruction Following Evaluation |
|---|
| IFEval |
| 32 |
| May 13, 2026 |
| Competitive Programming | CodeForces | 32 | May 14, 2026 |
|---|
| Document Understanding | DUDE | 32 | May 15, 2026 |
|---|
| Text-to-Image Generation | DrawBench | 32 | Apr 28, 2026 |
|---|
| Locomotion | Dog & Humanoid suite | 32 | Feb 26, 2026 |
|---|
| Code Generation | APPS Intermediate | 32 | Feb 27, 2026 |
|---|
| Response correctness and completeness evaluation | Coding | 32 | Feb 26, 2026 |
|---|
| Response correctness and completeness evaluation | Medical Q. | 32 | Feb 26, 2026 |
|---|
| Response correctness and completeness evaluation | Math | 32 | Feb 26, 2026 |
|---|
| Plane-level room detection | LiDAR S-dataset Simulation (S1-S7 and Avg) | 32 | Feb 26, 2026 |
|---|
| Color Constancy | All scenes (combined) | 32 | Feb 26, 2026 |
|---|
| Color Constancy | Outdoor scenes | 32 | Feb 26, 2026 |
|---|
| Color Constancy | Indoor Scenes (IN) | 32 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | IMO-Answer-Bench | 32 | May 26, 2026 |
|---|
| Mathematical Reasoning | AIME 2025 | 32 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | AIME 2024 | 32 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | GSM8K | 32 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | Beyond-AIME v1 (test) | 32 | Feb 26, 2026 |
|---|
| Question Answering | GPQA Diamond v1 (test) | 32 | Feb 26, 2026 |
|---|
| Symbolic Regression | Oscillator 1 (OOD) | 32 | May 19, 2026 |
|---|