Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 284 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-term forecasting | 9 datasets average | 60 | Apr 13, 2026 | ||
| Backdoor Attack Success Rate | Sentiment-140 | 60 | Apr 10, 2026 | ||
| Backdoor Attack Success Rate | CIFAR-10 | 60 | Apr 10, 2026 | ||
| Backdoor Attack Success Rate | MNIST | 60 | Apr 10, 2026 | ||
| Medical LLM Risk Triage | RETINA-SAFE Stage-1 | 60 | Apr 8, 2026 | ||
| Math Reasoning | AIME 2025 | 60 | May 18, 2026 | ||
| Computerized Adaptive Testing | SLP-Math | 60 | Apr 7, 2026 | ||
| Amorphous material generation | a-Si | 60 | Apr 1, 2026 | ||
| Semantic Similarity | SimLex | 60 | Apr 1, 2026 | ||
| Symbolic Regression | Feynman benchmark | 60 | Mar 31, 2026 | ||
| Function fitting | Feynman | 60 | Mar 31, 2026 | ||
| Visual Perception and Reasoning | V* | 60 | Jun 24, 2026 | ||
| Clustering | COL2 | 60 | Mar 31, 2026 | ||
| Constrained Clustering | COL2 | 60 | Mar 31, 2026 | ||
| Reasoning | Big-Bench Hard (BBH) | 60 | Jun 29, 2026 | ||
| Object Detection | Vehicle Detection (test) | 60 | Mar 30, 2026 | ||
| Spectral Unmixing | BioSR Microtubule/CCP, mTurquoise, 5-band v1 (test) | 60 | Mar 26, 2026 | ||
| Adversarial Example Detection | LibriSpeech C&W attack vs. benign | 60 | Mar 25, 2026 | ||
| Road Network-based Trajectory Generation | ShenZhen | 60 | Mar 25, 2026 | ||
| Gaze Estimation | MPIIFaceGaze | 60 | Jun 11, 2026 | ||
| RCC classification | RCC @ Friction | 60 | Mar 20, 2026 | ||
| Mathematical Reasoning | Olympiad | 60 | Jun 19, 2026 | ||
| Perceived risk prediction | LC Scenario | 60 | Mar 17, 2026 | ||
| 3D Intention Prediction | MoGaze | 60 | Mar 17, 2026 | ||
| 3D Intention Prediction | CIRCLE | 60 | Mar 17, 2026 |