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 |
|---|---|---|---|---|---|
| Global Weather Forecasting | ERA5 lite | 108 | May 28, 2026 | ||
| Robotic Manipulation | LIBERO | 108 | Jun 23, 2026 | ||
| Legal case grading agreement | Public law | 108 | May 21, 2026 | ||
| Legal case grading agreement | Criminal law | 108 | May 21, 2026 | ||
| Black-box Adversarial Attack | ModelNet40 | 108 | May 20, 2026 | ||
| Linear Regression |
| LHSM m=16 (test) |
| 108 |
| May 19, 2026 |
| Linear Regression | LHSM (test) | 108 | May 19, 2026 |
|---|
| Reranking | TREC DL 2019 v1 (test) | 108 | May 15, 2026 |
|---|
| Document Reranking | TREC DL 2019 and 2020 (test) | 108 | May 15, 2026 |
|---|
| Reranking | TREC DL 2019 (test) | 108 | May 15, 2026 |
|---|
| Medical Image Synthesis | BraTS | 108 | May 12, 2026 |
|---|
| Classification | CIFAR-10 | 108 | May 11, 2026 |
|---|
| Linguistic Acceptability | CoLA | 108 | Jul 1, 2026 |
|---|
| Science Question Answering | ARC Easy | 108 | Jun 24, 2026 |
|---|
| Backdoor Defense | CIFAR-10 | 108 | Jul 8, 2026 |
|---|
| Kernel Speedup | Synthetic Large Configuration (D=8192, V=128k) | 108 | Mar 18, 2026 |
|---|
| Commonsense Reasoning | CommonsenseQA | 108 | May 4, 2026 |
|---|
| Text-to-Image Generation | GenEval | 108 | Apr 28, 2026 |
|---|
| Reasoning | 7-benchmark commonsense and reading-comprehension suite (ARC-Easy, ARC-Challenge, HellaSwag, WinoGrande, PIQA, BoolQ, and OpenBookQA) LM Evaluation Harness default (test) | 108 | Feb 26, 2026 |
|---|
| Watermark Detection | Stable Diffusion-Prompts (SDP) 350 watermarked images | 108 | Feb 26, 2026 |
|---|
| Traffic State Estimation | I-24 MOTION 200x200 grids (unobserved pixels) | 108 | Feb 26, 2026 |
|---|
| Long-context understanding | LongBench 1.0 (test) | 108 | Jun 24, 2026 |
|---|
| Autonomous Driving Planning | NAVSIM Navhard v2 | 108 | Jun 16, 2026 |
|---|
| Video Depth Estimation | Bonn | 108 | Apr 24, 2026 |
|---|
| Classification | SST2 | 108 | Jun 5, 2026 |
|---|