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 |
|---|---|---|---|---|---|
| Image Classification | Cifar100 LT | 48 | Mar 26, 2026 | ||
| Automatic Speech Recognition | LibriSpeech Psychoacoustic attack | 48 | Mar 25, 2026 | ||
| Automatic Speech Recognition | LibriSpeech C&W attack | 48 | Mar 25, 2026 | ||
| Digital Watermarking | IndicSideFace 33 | 48 | Mar 25, 2026 | ||
| Mutation Killing | MN (Killable) | 48 | Mar 25, 2026 | ||
| Jailbreak Attack |
| AdvBench |
| 48 |
| Apr 14, 2026 |
| Backdoor Attack | Misuse | 48 | Apr 15, 2026 |
|---|
| Backdoor Attack | DAN (Do-Anything-Now) | 48 | Apr 15, 2026 |
|---|
| Gradient computation | Workload 32,768 tokens | 48 | Mar 24, 2026 |
|---|
| Video Understanding | MVBench, EgoSchema, MLVU, LongVideo Bench, and VideoMME | 48 | Mar 24, 2026 |
|---|
| Knowledge Base Question Answering | GrailQA Freebase (test) | 48 | Jun 2, 2026 |
|---|
| Multi-agent discussion attack | MMMU | 48 | Mar 24, 2026 |
|---|
| Sound Speed Profile (SSP) Estimation | GDCSM_Argo (1975 m depth) | 48 | Mar 24, 2026 |
|---|
| Sound Speed Profile (SSP) Estimation | GDCSM_Argo 1000 m depth | 48 | Mar 24, 2026 |
|---|
| Mathematical Reasoning | AMC 2023 | 48 | May 4, 2026 |
|---|
| Nudity Erasure | Nudity Erasure | 48 | Mar 19, 2026 |
|---|
| Clustering | Sensorless Drive Diagnosis | 48 | Mar 19, 2026 |
|---|
| Clustering | 3D Road Network | 48 | Mar 19, 2026 |
|---|
| Clustering | Covertype | 48 | Mar 19, 2026 |
|---|
| Clustering | Protein Homology m=145,751, n=74 (test) | 48 | Mar 19, 2026 |
|---|
| Clustering | KEGG Metabolic | 48 | Mar 19, 2026 |
|---|
| Clustering | Range Queries Aggregates m = 200,000, n = 7 1.0 | 48 | Mar 19, 2026 |
|---|
| Clustering | MFCCs for Speech Emotion Recognition | 48 | Mar 19, 2026 |
|---|
| Clustering | Pla85900 | 48 | Mar 19, 2026 |
|---|
| Clustering | Skin Segmentation (full) | 48 | Mar 19, 2026 |
|---|