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 |
|---|---|---|---|---|---|
| Computation Time Estimation | V2X Security Messages (IEEE 1609.2) on Raspberry Pi 4 | 30 | Jun 15, 2026 | ||
| Security Message Computation | Android Platform | 30 | Jun 15, 2026 | ||
| Message Length Evaluation | IEEE 1609.2 and IEEE 1609.2.1 Messages | 30 | Jun 15, 2026 | ||
| Question Classification | TREC50 | 30 | Jun 15, 2026 | ||
| Network Event Evolution Simulation | Net-E SD v2-6.5M (test) |
| 30 |
| Jun 12, 2026 |
| 3D Chern-Simons prediction | Kühn 3-torus L=8 (test) | 30 | Jun 12, 2026 |
|---|
| 3D Chern-Simons prediction | Kühn 3-torus L=8 (train) | 30 | Jun 12, 2026 |
|---|
| Black-box Adversarial Motion Attack | 100STYLE | 30 | Jun 12, 2026 |
|---|
| Prompt Injection Detection | AgentDyn | 30 | Jun 12, 2026 |
|---|
| Prompt Injection Detection | AgentDojo | 30 | Jun 12, 2026 |
|---|
| Recommendation | Xing (warm) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Xing (cold) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Xing (overall) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Citeulike (warm) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Citeulike (cold) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Citeulike (overall) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Movielens (warm) | 30 | Jun 11, 2026 |
|---|
| Recommendation | Movielens (cold) | 30 | Jun 11, 2026 |
|---|
| Label Correction | AGNews | 30 | Jun 11, 2026 |
|---|
| Image Classification | Skewed MNIST | 30 | Jun 11, 2026 |
|---|
| Safety Evaluation | XSTest | 30 | Jun 11, 2026 |
|---|
| Truthful Question Answering | TruthfulQA | 30 | Jun 11, 2026 |
|---|
| Mathematical Reasoning | GSM8K | 30 | Jun 11, 2026 |
|---|
| Medical Image Denoising | UPID Base | 30 | Jun 11, 2026 |
|---|
| Text Classification | IMDB | 30 | Jun 11, 2026 |
|---|