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 |
|---|---|---|---|---|---|
| Retrieval | CLERC | 30 | Mar 25, 2026 | ||
| Retrieval | COLIEE | 30 | Mar 25, 2026 | ||
| Map Query Efficiency | uav_flight | 30 | Mar 24, 2026 | ||
| Map Update | uav_flight | 30 | Mar 24, 2026 | ||
| Knowledge Intensive | Gaokao History | 30 | Mar 24, 2026 | ||
| Machine-generated text detection | WritingPrompts |
| 30 |
| Apr 21, 2026 |
| Machine-generated text detection | SQuAD | 30 | Jun 4, 2026 |
|---|
| Generative Engine Optimization | GEO-Bench in-domain | 30 | Mar 24, 2026 |
|---|
| Generative Engine Optimization | E-Commerce | 30 | Mar 24, 2026 |
|---|
| Generative Engine Optimization | MS MARCO | 30 | Mar 24, 2026 |
|---|
| Optic Cup and Disc Segmentation | Fundus image dataset Average | 30 | Mar 27, 2026 |
|---|
| Domain-Specific Applied Tasks | Education, Customer Support Q&A, Information Processing, Intention Recognition, Information Extraction, Complex Workflow | 30 | Mar 24, 2026 |
|---|
| Reward Scoring | HHA benchmark | 30 | Mar 24, 2026 |
|---|
| Token Attribution Faithfulness | SQuAD v2.0 | 30 | Mar 23, 2026 |
|---|
| Ripple effect magnitude prediction (ℓ2 logit shift) | Curated ripple-effect corpus 1.0 (test) | 30 | Mar 23, 2026 |
|---|
| Ripple effect magnitude prediction (|Δ log P(y)|) | Curated ripple-effect corpus 1.0 (test) | 30 | Mar 23, 2026 |
|---|
| Inference Throughput | Qwen3 Models (test) | 30 | Mar 23, 2026 |
|---|
| Inference Throughput | Qwen3 Query Projection Module NVIDIA A40 | 30 | Mar 23, 2026 |
|---|
| Federated Learning Classification | RCC ALL (test) | 30 | Mar 20, 2026 |
|---|
| Medical Question Answering | MedQA | 30 | Mar 20, 2026 |
|---|
| Financial Question Answering | FinQA | 30 | May 18, 2026 |
|---|
| Node Classification | Flickr | 30 | Mar 20, 2026 |
|---|
| Node Classification | Pubmed | 30 | Mar 20, 2026 |
|---|
| Node Classification | Citeseer | 30 | Mar 20, 2026 |
|---|
| Node Classification | Cora | 30 | Mar 20, 2026 |
|---|