Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 942 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Trace-level safety monitoring | TRACE | 28 | Apr 14, 2026 | ||
| Trace-level detection | TRACE | 28 | Apr 14, 2026 | ||
| Sabotage Detection | TRACE | 28 | Apr 14, 2026 | ||
| Case-level safety detection | TRACE | 28 | Apr 14, 2026 | ||
| Character description generation | BookWorm | 28 | Apr 14, 2026 | ||
| Hallucination Detection | UMWP | 28 | Apr 14, 2026 | ||
| Hallucination Detection | SQuAD v2 | 28 | Apr 14, 2026 | ||
| Medical Question Answering | MedMCQA | 28 | May 28, 2026 | ||
| Multi-modal Reasoning | MMStar | 28 | Apr 21, 2026 | ||
| Image-to-Image Translation | CD3 (test) | 28 | Apr 14, 2026 | ||
| Unconditional Image Generation | AFHQ 10k v2 64x64 | 28 | Apr 13, 2026 | ||
| Unconditional Image Generation | FFHQ 10k 64x64 | 28 | Apr 13, 2026 | ||
| Mathematical Reasoning | MATH500 | 28 | Jun 4, 2026 | ||
| Scanpath Prediction | Scanpath Prediction Dataset | 28 | Apr 13, 2026 | ||
| Multimodal Evaluation | Combined Benchmark Suite (GQA, MMB, MME, VQA-T, SQA-I, VQA-v2) | 28 | Apr 13, 2026 | ||
| Data Exfiltration via Indirect Prompt Injection | Indirect Prompt Injection Dataset 1.0 (test) | 28 | Apr 13, 2026 | ||
| Low-Light Image Enhancement | MILL-s DSLR | 28 | Apr 10, 2026 | ||
| Graph Classification | AMotif basis OOD | 28 | Apr 10, 2026 | ||
| Semantic Segmentation | VOC 21 (val) | 28 | Apr 10, 2026 | ||
| Batch incremental 3D object detection | ScanNet V2 (val) | 28 | Apr 10, 2026 | ||
| Robotic Manipulation | LIBERO Spatial | 28 | Jun 2, 2026 | ||
| Classification | knowledge | 28 | Apr 10, 2026 | ||
| Classification | pop failures | 28 | Apr 10, 2026 | ||
| Classification | plrx | 28 | Apr 10, 2026 | ||
| Classification | fertility | 28 | Apr 10, 2026 |