Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2368 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Brain Age Prediction | 3D Brain MRI Multi-site Cohort (test) | 15 | Jun 9, 2026 | ||
| Multivariate Long-term Time Series Forecasting | Electricity | 15 | Jun 29, 2026 | ||
| Early Failure Detection | LIBERO Unseen | 15 | Jun 9, 2026 | ||
| Early Failure Detection | LIBERO (Seen) | 15 | Jun 9, 2026 | ||
| Instructional Temporal Answer Grounding in Video | CMIVQA (test) | 15 | Jun 9, 2026 | ||
| Geometric Primitive Signature Prediction | RGBD-Art (test) | 15 | Jun 9, 2026 | ||
| GPS Prediction | HOI4D (test) | 15 | Jun 9, 2026 | ||
| Language Modeling | OpenWebText | 15 | Jun 17, 2026 | ||
| Free-form summarization | HELMET multi_lexsum | 15 | Jun 9, 2026 | ||
| Downstream Prediction | US | 15 | Jun 9, 2026 | ||
| Downstream Prediction | China | 15 | Jun 9, 2026 | ||
| Downstream Prediction | Changsha | 15 | Jun 9, 2026 | ||
| Layout Detection | PereStruct (test) | 15 | Jun 9, 2026 | ||
| Tool Retrieval | GeoPlan-bench (Overall) | 15 | Jun 9, 2026 | ||
| Instruction Following | CFBench | 15 | Jun 9, 2026 | ||
| Multi-hop Question Answering | Bamboogle OOD | 15 | Jun 9, 2026 | ||
| Multi-hop Question Answering | 2WikiMultihopQA OOD | 15 | Jun 9, 2026 | ||
| General Question Answering | PopQA OOD | 15 | Jun 9, 2026 | ||
| General Question Answering | TriviaQA OOD | 15 | Jun 9, 2026 | ||
| Jailbreak Detection | GCG attacks, Databricks Dolly 15K, and OR-Bench PMPs (test) | 15 | Jun 8, 2026 | ||
| AI-generated text detection | DetectRL Multi-Attack | 15 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Review | 15 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Writing | 15 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL XSum | 15 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL ArXiv | 15 | Jun 8, 2026 |