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 |
|---|---|---|---|---|---|
| Word Similarity | RG-65 (test) | 33 | Feb 26, 2026 | ||
| Counterfactual Input Evaluation | CrowS-Pairs | 33 | Feb 26, 2026 | ||
| Feature Attribution Evaluation | ImageNet 1k (val) | 33 | Feb 26, 2026 | ||
| Question Answering | BBH | 33 | May 22, 2026 | ||
| WSI Classification | CAMELYON17 (test) |
| 33 |
| Feb 26, 2026 |
| Object Classification | ImageNet-1K | 33 | Feb 26, 2026 |
|---|
| Video Action Classification | COIN | 33 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | AMC 2023 (test) | 33 | Jun 4, 2026 |
|---|
| Image Classification | CelebA and CelebA-CF | 32 | Jul 9, 2026 |
|---|
| MRI Reconstruction | Gated cardiac MRI data | 32 | Jul 7, 2026 |
|---|
| Camera pose estimation | 7Scenes | 32 | Jul 7, 2026 |
|---|
| Question Answering | RULER HQA | 32 | Jul 3, 2026 |
|---|
| Autoregressive Image Generation | Harmon | 32 | Jul 2, 2026 |
|---|
| Question Answering | 2WikiMultihopQA | 32 | Jul 2, 2026 |
|---|
| Question Answering | MuSiQue | 32 | Jul 2, 2026 |
|---|
| Question Answering | HotpotQA | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | Wikipedia (Average) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | NUS-WIDE (Average) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | Wikipedia (Unseen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | Pascal Sentence (Unseen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | NUS-WIDE (Unseen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | MIR Flickr (Unseen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | Pascal Sentence (Seen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | NUS-WIDE (Seen) | 32 | Jul 2, 2026 |
|---|
| Cross-modal Retrieval | MIR Flickr (Seen) | 32 | Jul 2, 2026 |
|---|