Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 899 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Reasoning | MM-Vista | 29 | Jun 30, 2026 | ||
| Image Classification | ImageNet-R | 29 | Jun 2, 2026 | ||
| Visuomotor Control | LIBERO | 29 | Jun 16, 2026 | ||
| Retrieval-style Queries | LinkedIn's Hiring Agent dataset Retrieval-style queries v1.0 (test) | 29 | Apr 30, 2026 | ||
| Summary-style Queries | LinkedIn's Hiring Agent Summary-style queries v1.0 (test) | 29 | Apr 30, 2026 | ||
| Long-form Question Answering | Retrieval-style queries | 29 | Apr 30, 2026 | ||
| Long-form Question Answering | Summary-style queries | 29 | Apr 30, 2026 | ||
| Zero-shot Evaluation | Eight tasks zero-shot | 29 | Apr 30, 2026 | ||
| Function Calling | BFCL | 29 | Apr 30, 2026 | ||
| Discriminative Object Hallucination | POPE MSCOCO Popular | 29 | Jun 1, 2026 | ||
| Discriminative Object Hallucination | POPE MSCOCO (Random) | 29 | Jun 1, 2026 | ||
| Knowledge Graph Completion | MKG-Y (test) | 29 | Apr 29, 2026 | ||
| Knowledge Graph Completion | DB15K (test) | 29 | Apr 29, 2026 | ||
| Spatial Understanding | CV-Bench | 29 | Jul 7, 2026 | ||
| Semantic Segmentation | ELU dataset | 29 | Apr 28, 2026 | ||
| Low-Light Novel View Synthesis | LLD | 29 | Apr 28, 2026 | ||
| Low-Light Novel View Synthesis | LOM full | 29 | Apr 28, 2026 | ||
| Low-Light Novel View Synthesis | NeRF360 | 29 | Apr 28, 2026 | ||
| Object Detection | AlphaDent (test) | 29 | Apr 28, 2026 | ||
| Image Classification | SVHN (test) | 29 | May 14, 2026 | ||
| Image Classification | WebVision 50 (test) | 29 | May 25, 2026 | ||
| Image Classification | CIFAR-10 18 (test) | 29 | Jul 7, 2026 | ||
| Slide Question Answering | SlideVQA | 29 | May 15, 2026 | ||
| Long-context language understanding | LongBench | 29 | Apr 24, 2026 | ||
| Terminal-related CLI agent task | TerminalBench 2.0 | 29 | Apr 23, 2026 |