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 |
|---|---|---|---|---|---|
| Color Image Recovery | Pepper color image | 42 | Mar 4, 2026 | ||
| Color Image Recovery | House color image | 42 | Mar 4, 2026 | ||
| Color Image Recovery | Airplane color image | 42 | Mar 4, 2026 | ||
| Time Series Forecasting | ACEA | 42 | Mar 4, 2026 | ||
| Time Series Forecasting | Exchange | 42 | Mar 4, 2026 | ||
| Time Series Forecasting |
| Beijing |
| 42 |
| Mar 4, 2026 |
| Time Series Forecasting | Solar | 42 | Mar 4, 2026 |
|---|
| Instruction Following | Self-Instruct (test) | 42 | Mar 5, 2026 |
|---|
| Instruction Following | Dolly Eval (test) | 42 | Mar 5, 2026 |
|---|
| Multi-objective search | Local Wiki Search | 42 | Mar 4, 2026 |
|---|
| Adversarial Attack on Neural Contextual Bandits | Yelp | 42 | Mar 4, 2026 |
|---|
| MLLM-as-a-judge evaluation | VL RewardBench | 42 | Apr 21, 2026 |
|---|
| Image Classification | CIFAR-10 10% label | 42 | Feb 27, 2026 |
|---|
| Fine-grained classification | Cars | 42 | Jun 8, 2026 |
|---|
| Image Classification | RSNA | 42 | Feb 27, 2026 |
|---|
| AI-generated text detection | Long-form QA 3K generations corpus | 42 | Feb 27, 2026 |
|---|
| Image Classification | CINIC-10 1.0 (10% label) | 42 | Feb 27, 2026 |
|---|
| Image Classification | SVHN 1.0 (10% label) | 42 | Feb 27, 2026 |
|---|
| Offline Reinforcement Learning | Antmaze Medium play offline (target domain) | 42 | Feb 26, 2026 |
|---|
| Spatial Logical Reasoning | SpatiaLQA | 42 | Feb 26, 2026 |
|---|
| Long-text-to-Image Generation | LongText-Bench | 42 | Jun 23, 2026 |
|---|
| Trajectory Planning | NAVSIM v1 (test) | 42 | Jul 2, 2026 |
|---|
| Dynamic Graph Anomaly Detection | Wikipedia S2 | 42 | Feb 26, 2026 |
|---|
| Dynamic Graph Anomaly Detection | MOOC S2 | 42 | Feb 26, 2026 |
|---|
| Blind Image Quality Assessment | LIVE | 42 | May 19, 2026 |
|---|