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 |
|---|---|---|---|---|---|
| Tabular Classification | Heart | 31 | Jun 11, 2026 | ||
| Multi-turn Agent Interaction | ALFWorld (test) | 31 | May 27, 2026 | ||
| Robot Manipulation | LIBERO 10 | 31 | Jul 8, 2026 | ||
| Multiclass Classification | Multiclass panel 3 healthcare datasets v1.0 (test) | 31 | May 19, 2026 | ||
| LLM Alignment Evaluation | Arena-Hard v0.1 |
| 31 |
| May 28, 2026 |
| Vision similarity grounding | ImageNet 100 | 31 | May 18, 2026 |
|---|
| Language similarity grounding | SST-2 | 31 | May 18, 2026 |
|---|
| Graph similarity grounding | Flickr | 31 | May 18, 2026 |
|---|
| Aggregate Benchmark Evaluation | Overall Performance Avg. | 31 | May 14, 2026 |
|---|
| Comprehensive Multimodal Benchmarking | MMBench MMB-EN_en | 31 | May 14, 2026 |
|---|
| Visual Question Answering | GQA | 31 | May 14, 2026 |
|---|
| Table Understanding | TableBench, WikiTQ, WikiSQL Aggregated | 31 | May 14, 2026 |
|---|
| Table Reasoning | TableBench | 31 | May 14, 2026 |
|---|
| Phenotyping | MIMIC-IV (test) | 31 | May 13, 2026 |
|---|
| ICU Mortality | MIMIC-IV (test) | 31 | May 13, 2026 |
|---|
| Safety Evaluation | HarmBench (test) | 31 | Jun 9, 2026 |
|---|
| General Reasoning | GPQA Diamond | 31 | Jun 9, 2026 |
|---|
| Fluid Dynamics Simulation | Navier-Stokes (NS) nu=10^-5 at 64x64 unified-protocol (test) | 31 | May 12, 2026 |
|---|
| Clustering | MNIST 10K | 31 | Jun 18, 2026 |
|---|
| Class-Incremental Learning | CIFAR100 5 tasks | 31 | May 13, 2026 |
|---|
| Protein-Protein Interaction | Bernett | 31 | May 11, 2026 |
|---|
| Peptide-HLA binding prediction | Peptide-HLA | 31 | May 11, 2026 |
|---|
| Graph Distribution Classification and Clustering | ER, RP, SBM, RG graph distributions | 31 | May 8, 2026 |
|---|
| Multi-Robot Multi-Unit Pre-marshalling Problem optimization | MR-MUPMP (train) | 31 | May 8, 2026 |
|---|
| Code Generation | LiveCodeBench v6 (2025-02 to 2025-05) | 31 | May 13, 2026 |
|---|