Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 542 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Continual Instruction Tuning | UCIT (Unified Continual Instruction Tuning) | 40 | Jun 23, 2026 | ||
| Medical Visual Question Answering (Multiple-Choice) | MIMIC (test) | 40 | May 12, 2026 | ||
| Medical Visual Question Answering (Multiple-Choice) | IU-XRay (test) | 40 | May 12, 2026 | ||
| Medical Visual Question Answering (True/False) | MIMIC (test) | 40 | May 12, 2026 | ||
| Medical Visual Question Answering (True/False) | IU-XRay (test) | 40 | May 12, 2026 | ||
| Multimodal Reasoning | RealWorldQA | 40 | May 19, 2026 | ||
| LLM Serving and Question Answering | MultiHopRAG hot0.7 (test) | 40 | May 12, 2026 | ||
| Hallucination Evaluation | A-HaluEval | 40 | May 12, 2026 | ||
| Mathematical Reasoning | HMMT Feb 2026 | 40 | May 21, 2026 | ||
| Novel View Synthesis | DL3DV | 40 | May 11, 2026 | ||
| Novel View Synthesis | AsyncEv-Deblur | 40 | May 11, 2026 | ||
| Differential Privacy Auditing | Xsum | 40 | May 11, 2026 | ||
| Privacy Auditing | Agnews | 40 | May 11, 2026 | ||
| Privacy Auditing | Trec | 40 | May 11, 2026 | ||
| Task-Incremental Learning | CIFAR-100 20 tasks | 40 | May 18, 2026 | ||
| Needle Retrieval | Needle In A Haystack | 40 | May 8, 2026 | ||
| Node Classification | CITESEER | 40 | May 8, 2026 | ||
| Image Classification | CIFAR-100 (test) | 40 | May 8, 2026 | ||
| Image Classification | CIFAR-10 (test) | 40 | May 8, 2026 | ||
| Classification | Radar Signal Processing Dataset (5-fold CV) | 40 | May 20, 2026 | ||
| Graph reconstruction | CiteSeer | 40 | Jun 9, 2026 | ||
| Graph reconstruction | Cora | 40 | Jun 9, 2026 | ||
| Adversarial Attack | 16 malicious prompts | 40 | May 6, 2026 | ||
| Voronoi regret minimization | Unit Hypercube (I^d) synthetic setup | 40 | May 4, 2026 | ||
| Multi-modal Stance Detection | MTSE | 40 | May 1, 2026 |