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 |
|---|---|---|---|---|---|
| Relation-Conditioned Retrieval | Elec | 30 | May 12, 2026 | ||
| Traffic State Estimation | I-24 MOTION 1.0 (20221202) | 30 | May 11, 2026 | ||
| Traffic State Estimation | I-24 MOTION 1.0 (20221129) | 30 | May 11, 2026 | ||
| Traffic State Estimation | I-24 MOTION 1.0 (20221123) | 30 | May 11, 2026 | ||
| Traffic State Estimation | I-24 MOTION 1.0 (20221122) | 30 |
| May 11, 2026 |
| Traffic State Estimation | I-24 MOTION 1.0 (20221121) | 30 | May 11, 2026 |
|---|
| 3D Point Cloud Classification | ModelNet40 (test) | 30 | May 11, 2026 |
|---|
| 3D Point Cloud Classification | ScanObjectNN (test) | 30 | May 11, 2026 |
|---|
| Enzyme Commission classification | EC | 30 | May 11, 2026 |
|---|
| Multi-domain Task-Incremental Learning | MTIL Order I (test) | 30 | May 20, 2026 |
|---|
| Online inertial parameter estimation | Inertial parameter estimation problems Teensy 4.1 MCU | 30 | May 11, 2026 |
|---|
| Retrieval Hijacking | Sample100 1.0 (test) | 30 | May 11, 2026 |
|---|
| Code Generation | MBPP v1 (plus) | 30 | May 11, 2026 |
|---|
| Code Generation | MBPP base v1 | 30 | May 11, 2026 |
|---|
| Code Generation | HumanEval+ v1 | 30 | May 11, 2026 |
|---|
| Code Generation | HumanEval base v1 | 30 | May 11, 2026 |
|---|
| Salient Object Detection | USOD | 30 | Jul 3, 2026 |
|---|
| Image Classification | ImageNet-1k random 100-class subsets 1.0 (test) | 30 | May 11, 2026 |
|---|
| Multi-turn planning | ALFWorld (test) | 30 | May 11, 2026 |
|---|
| Downstream skill execution | SkillsBench (test) | 30 | May 11, 2026 |
|---|
| Eye Movement Biometric Authentication (TEX task) | GazeBaseVR | 30 | May 11, 2026 |
|---|
| Eye Movement Biometric Authentication (TEX task) | GazeBase | 30 | May 11, 2026 |
|---|
| Error Attribution | MATH | 30 | May 11, 2026 |
|---|
| Error Attribution | GSM8k Right Dense | 30 | May 11, 2026 |
|---|
| Error Attribution | GSM8k Mid Dense | 30 | May 11, 2026 |
|---|