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 |
|---|---|---|---|---|---|
| Question Answering | AmbigQA | 36 | May 26, 2026 | ||
| Out-of-Distribution Action Detection | THUMOS14 | 36 | May 26, 2026 | ||
| Policy Learning | HIV dataset | 36 | May 26, 2026 | ||
| Uncertainty Estimation | Real-Noise | 36 | May 26, 2026 | ||
| Code Generation | MBPP | 36 | Jul 1, 2026 | ||
| Long-form generation hallucination evaluation |
| CHAIR |
| 36 |
| May 26, 2026 |
| Network Alignment | ACM-DBLP-A | 36 | May 26, 2026 |
|---|
| Network Alignment | ACM-DBLP-P | 36 | May 26, 2026 |
|---|
| Network Alignment | Phone-Email | 36 | May 26, 2026 |
|---|
| Secure Code Generation | LLMSecEval 150 tasks | 36 | May 26, 2026 |
|---|
| Fault Detection | Cifar-100 | 36 | May 26, 2026 |
|---|
| Fault Detection | Cifar-10 | 36 | May 26, 2026 |
|---|
| Audio Understanding Robustness | MMAU Sound (SNR=-10dB) | 36 | May 26, 2026 |
|---|
| Action Recognition | HMDB-51 | 36 | May 25, 2026 |
|---|
| Reasoning | 15 reasoning benchmarks weighted mean (test) | 36 | May 25, 2026 |
|---|
| Mathematical Reasoning | HMMT25 | 36 | Jun 9, 2026 |
|---|
| Motion-compensated 3D Brain MRI Reconstruction | FastMRI multicoil T1-weighted (test) | 36 | May 22, 2026 |
|---|
| Clinical diagnosis | S3 1.0 (test) | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Banknote | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Vehicle | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Yeast | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Waveform | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Segment | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Spambase | 36 | May 22, 2026 |
|---|
| Class Prior Estimation | Diabetes | 36 | May 22, 2026 |
|---|