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 |
|---|---|---|---|---|---|
| Preference Alignment | HH-RLHF | 45 | Jun 26, 2026 | ||
| Question Answering and Commonsense Reasoning | Short-context benchmarks ARC-C, ARC-E, PIQA, Winogrande, HellaSwag | 45 | Apr 21, 2026 | ||
| Gesture Recognition | GrabMyo (cross-subject) | 45 | Mar 6, 2026 | ||
| Upvote Prediction | Stackexchange | 45 | Mar 5, 2026 | ||
| Churn Prediction | Stackexchange |
| 45 |
| Mar 5, 2026 |
| Conversion Rate Prediction | Retailrocket | 45 | Mar 5, 2026 |
|---|
| CTR Prediction | Outbrain Small | 45 | Mar 5, 2026 |
|---|
| CTR Prediction | Diginetica | 45 | Mar 5, 2026 |
|---|
| Text-to-Structure Extraction | T2S-Bench-E2E 1.0 (test) | 45 | Mar 5, 2026 |
|---|
| Multi-hop Multiple-choice Question Answering | T2S-Bench-MR 1.0 (test) | 45 | Mar 5, 2026 |
|---|
| Object Detection | M3FD | 45 | May 8, 2026 |
|---|
| Traffic Sign Classification | Traffic Sign dataset | 45 | Mar 4, 2026 |
|---|
| Reasoning Quality Correlation Analysis | PolitiFact | 45 | Mar 4, 2026 |
|---|
| Reasoning Quality Correlation Analysis | LIAR | 45 | Mar 4, 2026 |
|---|
| Color Gaussian Denoising | Urban100 | 45 | May 26, 2026 |
|---|
| Fact-based Question Answering | FVQA (test) | 45 | Jun 5, 2026 |
|---|
| Referring Remote Sensing Image Segmentation | RefSegRS (test) | 45 | Jun 30, 2026 |
|---|
| Training Data Extraction | URL PII | 45 | Feb 27, 2026 |
|---|
| Training Data Extraction | Phone PII | 45 | Feb 27, 2026 |
|---|
| Training Data Extraction | Email PII | 45 | Feb 27, 2026 |
|---|
| Imputation | PhysioNet Natural (80%) + Additional Missing 2012 | 45 | Feb 26, 2026 |
|---|
| Zero-shot Multiple Choice Question Answering | NLP Common Sense Reasoning Suite (HS, WG, OBQA, ARC-E, ARC-C, PIQA, SIQA, Story) zero-shot | 45 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Sen1Floods11 | 45 | May 28, 2026 |
|---|
| Thematic fit estimation | McRae | 45 | Feb 26, 2026 |
|---|
| Thematic fit estimation | Pado | 45 | Feb 26, 2026 |
|---|