Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 939 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | BABEL 75% OR | 28 | May 1, 2026 | ||
| Action Recognition | BABEL 50% OR | 28 | May 1, 2026 | ||
| Action Recognition | BABEL 25% OR | 28 | May 1, 2026 | ||
| Linux Privilege Escalation | Linux Privilege Escalation Benchmark 1.0 (test) | 28 | May 1, 2026 | ||
| Video Action Recognition | SSV2 (test) | 28 | Apr 30, 2026 | ||
| Multimodal Recommendation | Amazon Baby | 28 | May 19, 2026 | ||
| Reasoning | GAIA text | 28 | Apr 30, 2026 | ||
| Mathematical Reasoning | Minerva 272 | 28 | Apr 30, 2026 | ||
| Mathematical Reasoning | OlympiadBench 675 | 28 | Apr 30, 2026 | ||
| Reasoning Question Answering | FinQA (test) | 28 | May 22, 2026 | ||
| Knowledge Graph Completion | MKG-W (test) | 28 | Apr 29, 2026 | ||
| Autonomous Driving Planning | Nav (test) | 28 | Jul 9, 2026 | ||
| Black-box Optimization | Crashy Branin | 28 | Apr 29, 2026 | ||
| Visual Reasoning | VLMs are Blind | 28 | May 22, 2026 | ||
| Fact Verification | M2RAG | 28 | Apr 28, 2026 | ||
| Image Captioning | M2RAG | 28 | Apr 28, 2026 | ||
| Multimodal Question Answering | M2RAG | 28 | Apr 28, 2026 | ||
| Backdoor Defense | BadEdit, VPI, BadChain, and EmbedX | 28 | Apr 28, 2026 | ||
| Out-of-Distribution Detection | ImageNet (ID) vs Places (OOD) (test) | 28 | Jun 25, 2026 | ||
| Out-of-Distribution Detection | ImageNet (ID) vs iNaturalist OOD (test) | 28 | Jun 25, 2026 | ||
| Out-of-Distribution Detection | ImageNet (ID) vs Textures (OOD) (test) | 28 | Jun 25, 2026 | ||
| Clinical Diagnosis Identification | MIMIC Ext CDM IV | 28 | Apr 28, 2026 | ||
| Predicting Language Model Output | HateBS | 28 | Apr 28, 2026 | ||
| Predicting Language Model Output | PH | 28 | Apr 28, 2026 | ||
| Predicting Language Model Output | IMDB | 28 | Apr 28, 2026 |