Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1103 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-hop Question Answering | HotpotQA | 25 | Jun 12, 2026 | ||
| Memory-Augmented Question Answering | LoCoMo Multi-hop | 25 | Jun 4, 2026 | ||
| Dialogue Topic Segmentation | VHF | 25 | Jun 1, 2026 | ||
| Safety Evaluation | ATBench | 25 | May 29, 2026 | ||
| Text Reconstruction | BBC News | 25 | May 29, 2026 | ||
| Web Task Success | OnlineMind2Web | 25 | Jun 23, 2026 | ||
| Continual Model Routing | CMRBench v1 (test) | 25 | May 28, 2026 | ||
| General Reasoning | MMLU | 25 | Jun 2, 2026 | ||
| Object Hallucination | POPE | 25 | Jun 4, 2026 | ||
| Explainable AI | CRAFTER-XAI-Bench (test) | 25 | May 28, 2026 | ||
| Dense Object Detection | Dense200 | 25 | Jul 8, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 25 | Jul 8, 2026 | ||
| Multimodal Reasoning | MMStar | 25 | Jun 1, 2026 | ||
| Data Exfiltration | Data Exfiltration | 25 | May 27, 2026 | ||
| Science Question Answering | ARC C | 25 | Jun 2, 2026 | ||
| GUI Agent Task Success | AndroidWorld (online) | 25 | May 27, 2026 | ||
| Time Series Anomaly Detection | KDD 21 | 25 | May 27, 2026 | ||
| Unsupervised clustering | BreastMNIST | 25 | May 26, 2026 | ||
| Unsupervised clustering | ADNI CN vs AD | 25 | May 26, 2026 | ||
| Unsupervised Clustering | PneumoniaMNIST | 25 | May 26, 2026 | ||
| Unsupervised Clustering | NIFD (unsupervised) | 25 | May 26, 2026 | ||
| Service and Safety Evaluation | OLABENCH | 25 | May 26, 2026 | ||
| Classification | CDC BRFSS 2015 (5×2 cross-validation) | 25 | May 26, 2026 | ||
| Terminal Agent Tasks | TerminalBench 2.0 | 25 | Jun 23, 2026 | ||
| Mathematical Reasoning | Minerva Math | 25 | May 26, 2026 |