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 |
|---|---|---|---|---|---|
| Membership Inference Attack | CIFAR-100 AVG forget set | 40 | Mar 10, 2026 | ||
| Membership Inference Attack | CIFAR-100 Low forget set | 40 | Mar 10, 2026 | ||
| Membership Inference Attack | CIFAR-100 Mid forget set | 40 | Mar 10, 2026 | ||
| Membership Inference Attack | CIFAR-100 High forget set | 40 | Mar 10, 2026 | ||
| VAE metric correlation with diffusion generation quality | ImageNet (val) |
| 40 |
| Mar 9, 2026 |
| Code-level Structured Extraction | PVminer | 40 | Jun 16, 2026 |
|---|
| Video Inpainting | DNARendering (test) | 40 | Mar 6, 2026 |
|---|
| Pedestrian Attribute Recognition | EventPAR (test) | 40 | Mar 23, 2026 |
|---|
| Dynamic Link Prediction | Contact (inductive split) | 40 | Jun 4, 2026 |
|---|
| Dynamic Link Prediction | Flights (inductive) | 40 | Jun 4, 2026 |
|---|
| Discrete-event world model generation | Discrete-Event World Models 7 Scenarios | 40 | Mar 5, 2026 |
|---|
| Wasserstein Distance Estimation | Fragmented hypercube | 40 | Mar 5, 2026 |
|---|
| Text-to-Image Generation | StructT2IBench (test) | 40 | Mar 10, 2026 |
|---|
| Satellite→Drone Geo-localization | SUES-200 300m | 40 | Mar 10, 2026 |
|---|
| Response Classification | EXPGUARD (test) | 40 | Mar 4, 2026 |
|---|
| Controllable robustness curve prediction | ER networks TDA condition | 40 | Mar 4, 2026 |
|---|
| Reward Modeling | PPE Correlation | 40 | Mar 4, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 40 | Mar 4, 2026 |
|---|
| Instruction Following | NaturalInstructions | 40 | Mar 4, 2026 |
|---|
| Safety Evaluation | SPA-VL | 40 | Mar 30, 2026 |
|---|
| Instruction Following | Pronoun Changing | 40 | Mar 4, 2026 |
|---|
| Bias Mitigation | Bias in Bios | 40 | Mar 4, 2026 |
|---|
| Multimodal Benchmarking | MMB | 40 | Apr 8, 2026 |
|---|
| Multilingual Reasoning | MT-AIME 24 | 40 | Mar 4, 2026 |
|---|
| General Reasoning | MMLU-R | 40 | Jun 1, 2026 |
|---|