Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 320 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Sentiment Analysis | CMU-MOSI 43 (test) | 56 | Feb 26, 2026 | ||
| Tabular Classification | TabArena Binary | 56 | Feb 26, 2026 | ||
| Regression | TabArena Regression | 56 | Feb 26, 2026 | ||
| Multiclass Classification | TabArena Multiclass (6) | 56 | Feb 26, 2026 | ||
| Regression | CARTE Regression 40 | 56 | Feb 26, 2026 | ||
| Jailbreak Attack | JBB-Behaviors | 56 | Feb 26, 2026 | ||
| Object-Goal Navigation | HM3D-OVON Seen-Synonyms (val) | 56 | Jun 2, 2026 | ||
| Robotic Manipulation | LIBERO-10 | 56 | Jun 12, 2026 | ||
| Neural Network Inference | ARM Embedded Processors inference latency | 56 | Feb 26, 2026 | ||
| lineage classification | SARS-CoV-2 sequences (test) | 56 | Feb 26, 2026 | ||
| Molecule Generation | QM9 | 56 | Feb 26, 2026 | ||
| Molecule Generation | QM9 2014 | 56 | Feb 26, 2026 | ||
| Molecule Generation | ZINC 250k 2012 | 56 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Office (test) | 56 | Jul 7, 2026 | ||
| Information Retrieval | MS MARCO (test) | 56 | May 29, 2026 | ||
| Novel View Synthesis | RE10K challenging views (test) | 56 | Feb 26, 2026 | ||
| Few-shot 3D Point Cloud Semantic Segmentation | S3DIS v1.2 (Area-5) | 56 | May 18, 2026 | ||
| Deepfake Detection | DFDCP (test) | 56 | Apr 24, 2026 | ||
| Motion Deblur | FFHQ | 56 | May 28, 2026 | ||
| Text-to-Image Generation | FLUX.1 (dev) | 56 | Feb 26, 2026 | ||
| Talking Head Generation | RAVDESS intra-identity 1.0 | 56 | Apr 23, 2026 | ||
| Object Detection | PTSD (test) | 56 | Feb 26, 2026 | ||
| Object Detection | MTSD (test) | 56 | Feb 26, 2026 | ||
| Video Reasoning | MVBench | 56 | Jul 7, 2026 | ||
| Multimodal Emotion Recognition | CMU-MOSEI (test) | 56 | Mar 17, 2026 |