Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2593 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sequential Recommendation | Amazon | 14 | Jun 25, 2026 | ||
| Open-ended Visual Question Answering | CXR-PA | 14 | Jun 25, 2026 | ||
| Open-ended Visual Question Answering | Covid19 | 14 | Jun 25, 2026 | ||
| Open-ended Visual Question Answering | SLAKE | 14 | Jun 25, 2026 | ||
| Open-ended Visual Question Answering | Med-CXR | 14 | Jun 25, 2026 | ||
| Multimodal Emotion Reasoning | MER-UniBench Aggregate | 14 | Jun 25, 2026 | ||
| Fine-grained Emotion Recognition | OV-MERD+ | 14 | Jun 25, 2026 | ||
| Basic Emotion Recognition | MELD | 14 | Jun 25, 2026 | ||
| Basic Emotion Recognition | MER 24 | 14 | Jun 25, 2026 | ||
| Sentiment Analysis | SIMS v2 | 14 | Jun 25, 2026 | ||
| Sentiment Analysis | SIMS | 14 | Jun 25, 2026 | ||
| Sentiment Analysis | MOSI | 14 | Jun 25, 2026 | ||
| Monocular Depth Estimation | MovingDrone v1 (test) | 14 | Jun 25, 2026 | ||
| Mathematical Reasoning | MathVista | 14 | Jun 25, 2026 | ||
| Multi-agent Continual Cooperation | MAMuJoCo Reward (Expert) | 14 | Jun 25, 2026 | ||
| Ordinal Classification | LEVXSensors | 14 | Jun 25, 2026 | ||
| Financial Agent Task | FinanceAgent-Terminal | 14 | Jun 24, 2026 | ||
| General AI Assistant Task | GAIA-127 | 14 | Jun 24, 2026 | ||
| Function Calling | BFCL Parity | 14 | Jun 24, 2026 | ||
| Visual Object Tracking | DiDi 58 (test) | 14 | Jun 24, 2026 | ||
| Long-term Visual Object Tracking and Segmentation | VOTS24 | 14 | Jun 24, 2026 | ||
| In-Image Machine Translation | Translatotron-V Romanian-English (test) | 14 | Jun 24, 2026 | ||
| Image Translation | Translatotron-V En-De (test) | 14 | Jun 24, 2026 | ||
| Fault Detection | UCI-PM | 14 | Jun 24, 2026 | ||
| Fault Detection | SECOM | 14 | Jun 24, 2026 |