Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1858 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Virtual Try-On and Animation | ViViD Dataset | 18 | Apr 7, 2026 | ||
| Virtual Try-On and Animation | Internet Dataset | 18 | Apr 7, 2026 | ||
| Image Matching | HardMatch | 18 | Apr 7, 2026 | ||
| Image Classification | ImageNet-1K | 18 | Apr 7, 2026 | ||
| Language Modeling | Hospitality (HS) | 18 | Apr 7, 2026 | ||
| Multimodal Research | In-house 2 | 18 | Apr 7, 2026 | ||
| Multimodal Research | In-house 1 | 18 | Apr 7, 2026 | ||
| Clinical Counseling Dialogue Evaluation | Session Rating Scale | 18 | Apr 7, 2026 | ||
| Question Answering | TruthfulQA | 18 | Apr 7, 2026 | ||
| Multitask Language Understanding | MMLU | 18 | Apr 7, 2026 | ||
| Classification | MNIST 10,000 samples (test) | 18 | Apr 7, 2026 | ||
| Video-level Deepfake Detection | Google DeepFake Detection (DFD) (test) | 18 | Apr 7, 2026 | ||
| Conditional Multi-component Generation | PolyMNIST | 18 | May 4, 2026 | ||
| Unconditional Multi-component Generation | PolyMNIST | 18 | May 4, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 18 | May 19, 2026 | ||
| Jailbreak Defense Evaluation | EMRA JQ | 18 | Apr 7, 2026 | ||
| Jailbreak Defense Evaluation | EMRA RQ | 18 | Apr 7, 2026 | ||
| Jailbreak Defense Evaluation | EMRA HQ | 18 | Apr 7, 2026 | ||
| Jailbreak Defense Evaluation | EMRA MTA | 18 | Apr 7, 2026 | ||
| Deceptive Defense | EMRA (test) | 18 | Apr 7, 2026 | ||
| Large Language Model Inference | Decode Phase BS=1 | 18 | Apr 7, 2026 | ||
| Flight Recommendation | Flight Recommendation Final 5th Round | 18 | Apr 7, 2026 | ||
| Flight Recommendation | Flight Recommendation 1st Round | 18 | Apr 7, 2026 | ||
| General Reasoning | AVG Reasoning Suite | 18 | May 14, 2026 | ||
| Backdoor Defense | Bank marketing (test) | 18 | Apr 7, 2026 |