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 |
|---|---|---|---|---|---|
| Model Editing | WikiBigEdit | 49 | Mar 11, 2026 | ||
| Model Editing | FEVER | 49 | Mar 11, 2026 | ||
| Time Series Forecasting | Exchange Rate | 49 | May 12, 2026 | ||
| Regression | california | 49 | May 13, 2026 | ||
| Object Navigation | HM3D v1 | 49 | Jul 1, 2026 | ||
| Long-context language modeling evaluation |
| RULER |
| 49 |
| May 29, 2026 |
| Multiple-choice QA | Multiple-Choice Suite | 49 | Mar 20, 2026 |
|---|
| Regression | wine | 49 | Mar 6, 2026 |
|---|
| Regression | sulfur | 49 | Mar 6, 2026 |
|---|
| Regression | superconduct | 49 | Mar 6, 2026 |
|---|
| Regression | fried | 49 | Mar 6, 2026 |
|---|
| dynamic link prediction | UN Trade (transductive) | 49 | Jun 4, 2026 |
|---|
| Video Reasoning Segmentation | ReVOS Overall | 49 | May 15, 2026 |
|---|
| Video Reasoning Segmentation | ReVOS Referring | 49 | May 15, 2026 |
|---|
| Text Classification | AGNews | 49 | Jun 11, 2026 |
|---|
| Face Forgery Detection | UADFV | 49 | May 29, 2026 |
|---|
| Reasoning | BBH 3-shot | 49 | Apr 10, 2026 |
|---|
| Knowledge Estimation | ProgFeed | 49 | Feb 26, 2026 |
|---|
| Knowledge Estimation | CodeWorkout | 49 | Feb 26, 2026 |
|---|
| Code Similarity | CodeWorkout (5-fold averaged) | 49 | Feb 26, 2026 |
|---|
| Reasoning | Countdown | 49 | Jun 2, 2026 |
|---|
| Graph Out-of-Distribution Detection | BZR (ID) COX2 (OOD) | 49 | Apr 1, 2026 |
|---|
| Knowledge-Intensive Visual Question Answering | E-VQA (test) | 49 | Jun 29, 2026 |
|---|
| Entity classification | RelBench rel-avito user-visits | 49 | Jun 4, 2026 |
|---|
| High-resolution Visual Understanding | HR-Bench 4K | 49 | May 12, 2026 |
|---|