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 | KodCode | 94 | Jun 9, 2026 | ||
| Reasoning | MATH 500 | 94 | May 11, 2026 | ||
| Image Classification | GTSRB (test) | 94 | Jun 2, 2026 | ||
| Mathematical Reasoning | CollegeMath (test) | 94 | May 1, 2026 | ||
| Multitask Language Understanding | MMLU (val) | 94 | May 29, 2026 | ||
| Backdoor Defense |
| CIFAR-10 (test) |
| 94 |
| Jun 19, 2026 |
| Long-context understanding | LongBench (test) | 94 | Jul 3, 2026 |
|---|
| Classification | Zero-shot Evaluation Suite (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA) | 94 | Mar 12, 2026 |
|---|
| Machine Translation | TED data (test) | 94 | Feb 26, 2026 |
|---|
| Node classification | Freebase | 94 | May 26, 2026 |
|---|
| Watermark Detection | Vicuna-7b 16k 50 samples v1.5 | 94 | Feb 26, 2026 |
|---|
| Zero-shot Reasoning | ARC-Easy zero-shot | 94 | Jun 4, 2026 |
|---|
| Text Classification | SUBJ | 94 | May 21, 2026 |
|---|
| Object Detection | FLIR (test) | 94 | Mar 26, 2026 |
|---|
| Cancer Classification | TCGA-BRCA | 94 | Jun 8, 2026 |
|---|
| Semantic Segmentation | PC-459 | 94 | Apr 28, 2026 |
|---|
| 3D Object Classification | ScanObjectNN PB_T50_RS | 94 | Jun 2, 2026 |
|---|
| Human Activity Recognition | REALDISP | 94 | Feb 26, 2026 |
|---|
| 3D Human Pose Estimation | Human3.6M (S9, S11) | 94 | Feb 27, 2026 |
|---|
| Audio-Visual Question Answering | MUSIC-AVQA (test) | 94 | Jul 7, 2026 |
|---|
| Node Classification | Cora inductive | 94 | Mar 16, 2026 |
|---|
| Image Classification | Oxford Pets | 94 | Apr 14, 2026 |
|---|
| Image Classification | Oxford 102 Flowers | 94 | Jun 2, 2026 |
|---|
| OOD detection | CIFAR-100 standard (test) | 94 | Feb 26, 2026 |
|---|
| Semantic Segmentation | GTA5 to {Cityscapes, Mapillary, BDD} (test) | 94 | Feb 26, 2026 |
|---|