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 |
|---|---|---|---|---|---|
| Code Generation | MBPP | 32 | Apr 16, 2026 | ||
| Traveling Salesman Problem | TSP5K generated | 32 | Jun 4, 2026 | ||
| Knowledge Base Question Answering | CWQ (ComplexWebQuestions) | 32 | Apr 15, 2026 | ||
| Mathematical Reasoning | DeepMath 2025 (test) | 32 | Apr 15, 2026 | ||
| Mathematical Reasoning | MATH 2021 (test) | 32 | Apr 15, 2026 |
| Single-ingredient odor classification | SMELLNET BASE | 32 | Apr 15, 2026 |
|---|
| Utility Evaluation | AgentDojo | 32 | Apr 14, 2026 |
|---|
| Attack Success Rate | InjecAgent | 32 | Apr 14, 2026 |
|---|
| Multi-task Language Understanding | MMLU Pro (test) | 32 | Jul 1, 2026 |
|---|
| Referring Camouflaged Object Detection | R2C7K | 32 | Apr 14, 2026 |
|---|
| Polish Board Certification Examinations | speakleash/PES 2018-2022 | 32 | Apr 14, 2026 |
|---|
| Link Prediction | US Legis. (inductive) | 32 | Jun 4, 2026 |
|---|
| Novel View Synthesis | RE10K large overlap | 32 | Jul 1, 2026 |
|---|
| Novel View Synthesis | RE10K (small overlap) | 32 | Jul 1, 2026 |
|---|
| Far OOD Detection | Texture (test) | 32 | Apr 14, 2026 |
|---|
| Far OOD Detection | Places | 32 | Apr 14, 2026 |
|---|
| OOD Detection | ImageNet protocol datasets averaged over 4 (test) | 32 | Apr 14, 2026 |
|---|
| Far Out-of-Distribution Detection | Texture | 32 | Apr 14, 2026 |
|---|
| Far Out-of-Distribution Detection | SUN | 32 | Apr 14, 2026 |
|---|
| Far OOD detection | iNaturalist (test) | 32 | Apr 14, 2026 |
|---|
| Data Extraction Attack | RAP | 32 | May 25, 2026 |
|---|
| Image Classification | Oxford-IIIT | 32 | Apr 14, 2026 |
|---|
| Image Classification | ImageNet-1k | 32 | Apr 15, 2026 |
|---|
| Multimodal Understanding | Standard Multimodal Evaluation Suite (GQA, MMBench, MME, TextVQA, ScienceQA, VQA v2) 1.5 (test val) | 32 | Apr 13, 2026 |
|---|
| Membership Proofing | Synthetic Membership Proof Sets | 32 | Apr 13, 2026 |
|---|