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 |
|---|---|---|---|---|---|
| Node Classification Explanation | BA-shapes | 32 | Jun 23, 2026 | ||
| Graph Classification Explanation | MUTAG | 32 | Jun 23, 2026 | ||
| Graph Classification Explanation | BA-2motif | 32 | Jun 23, 2026 | ||
| Time to First Token (TTFT) | NVFP4-W4A16 | 32 | Jun 19, 2026 | ||
| Mobile GUI Navigation | MobileWorld GUI-Only 117 tasks (test) | 32 |
| Jun 19, 2026 |
| Hallucination Detection | QALD English 10 | 32 | Jun 19, 2026 |
|---|
| Hallucination Detection | WebQSP | 32 | Jun 19, 2026 |
|---|
| Hallucination Detection | GrailQA | 32 | Jun 19, 2026 |
|---|
| Sponsored Search Conversion | Criteo Sponsored Search Conversion (val) | 32 | Jun 18, 2026 |
|---|
| Regional Precipitation Forecasting (36 Hours lead time) | ERA5-CH regional forecast 0.25 degree | 32 | Jun 18, 2026 |
|---|
| Regional Precipitation Forecasting (24 Hours lead time) | ERA5-CH regional forecast 0.25 degree | 32 | Jun 18, 2026 |
|---|
| Regional Precipitation Forecasting (12 Hours lead time) | ERA5-CH regional forecast 0.25 degree | 32 | Jun 18, 2026 |
|---|
| Unconditional Dialogue Generation | Fisher (test) | 32 | Jun 18, 2026 |
|---|
| Hallucination Detection | Machine Translation | 32 | Jun 18, 2026 |
|---|
| Hallucination Detection | Summarization | 32 | Jun 18, 2026 |
|---|
| Hallucination Detection | QA | 32 | Jun 18, 2026 |
|---|
| Low-light Image Enhancement | LSRW NIKON (test) | 32 | Jun 17, 2026 |
|---|
| Low-light Image Enhancement | LOL | 32 | Jun 17, 2026 |
|---|
| Image Denoising | SSID CosPGD, 10 attack iterations | 32 | Jun 17, 2026 |
|---|
| Action Recognition | MECCANO (test) | 32 | Jun 17, 2026 |
|---|
| Math Reasoning | AIME 25 | 32 | Jun 16, 2026 |
|---|
| Math Reasoning | AMC 23 | 32 | Jun 16, 2026 |
|---|
| Image Classification | ImageNet-1K (val) | 32 | Jun 16, 2026 |
|---|
| Speech Deepfake Detection | CodecFake (CF) seen setting | 32 | Jun 16, 2026 |
|---|
| Speech Deepfake Detection | SeaCF (seen setting) | 32 | Jun 16, 2026 |
|---|