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 |
|---|---|---|---|---|---|
| Mathematical reasoning | Minerva Math | 51 | Jun 30, 2026 | ||
| Dynamic Link Prediction | Enron (transductive) | 51 | Jul 7, 2026 | ||
| Offline Multi-Objective Optimization | Off-MOO-Bench | 51 | Jun 16, 2026 | ||
| 3D Semantic Occupancy Prediction | nuScenes-Occupancy (val) | 51 | Jul 7, 2026 | ||
| Error Prediction | TriviaQA (val) | 51 | Jun 2, 2026 | ||
| Scientific Question Answering |
|---|
| GPQA |
| 51 |
| Jul 8, 2026 |
| Determiner Productivity Evaluation | Manchester child dyads (test) | 51 | May 28, 2026 |
|---|
| Automatic Speech Recognition | Arabic dataset | 51 | May 28, 2026 |
|---|
| Multiple Choice Question Answering | MMLU-PRO zero-shot | 51 | May 21, 2026 |
|---|
| Compressible Navier-Stokes (Comp-2D) | VICON (test) | 51 | May 19, 2026 |
|---|
| Sentiment Analysis | SST-2 | 51 | Jun 4, 2026 |
|---|
| Novel View Synthesis | Deep Blending | 51 | Jul 2, 2026 |
|---|
| Multi-Hop Question Answering | MuSiQue | 51 | May 20, 2026 |
|---|
| Excel Formula Generation | WikiTableQuestions (WikiTQ) 639 problems solvable in Excel (test) | 51 | May 13, 2026 |
|---|
| Face forgery detection | GenFace DDPM (test) | 51 | May 12, 2026 |
|---|
| Visual Question Answering | Text-Rich Evaluation Suite (OCR Bench, Text VQA, Chart QA, Doc VQA, Info VQA, Math Vista) | 51 | May 12, 2026 |
|---|
| Visual Grounding | HRBench8K | 51 | Jun 16, 2026 |
|---|
| PDE Solving | Darcy | 51 | Jun 30, 2026 |
|---|
| Instruction Following | Alpaca | 51 | May 13, 2026 |
|---|
| AI-generated image detection | GenImage (test) | 51 | Jun 8, 2026 |
|---|
| Physical Commonsense Reasoning | PIQA | 51 | Jun 29, 2026 |
|---|
| Node Classification | CiteSeer | 51 | May 26, 2026 |
|---|
| Terminal-related CLI agent task | TerminalBench 1.0 | 51 | Jun 23, 2026 |
|---|
| Fault Intensity Diagnosis | Cavitation-Noise | 51 | Apr 21, 2026 |
|---|
| Fault Intensity Diagnosis | Cavitation-Long | 51 | Apr 21, 2026 |
|---|