Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1047 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Agentic Task | AppWorld N (test) | 26 | Jun 1, 2026 | ||
| Agentic Task | ALFWorld Unseen | 26 | Jun 1, 2026 | ||
| Agentic Task | ALFWorld Seen | 26 | Jun 1, 2026 | ||
| Sentiment Analysis | SST-2 | 26 | Jun 4, 2026 | ||
| Robot Navigation | Corridor DoN sweep | 26 | May 29, 2026 | ||
| Anomaly Detection | Kaputt | 26 | May 29, 2026 | ||
| Anomaly Detection | LAG | 26 | May 29, 2026 | ||
| Anomaly Detection | MVTec LOCO | 26 | May 29, 2026 | ||
| React UI Generation | Cookie-Bench Overall | 26 | May 29, 2026 | ||
| React UI Generation | Cookie-Bench (Dynamic split) | 26 | May 29, 2026 | ||
| Simulation Performance | R2 | 26 | May 28, 2026 | ||
| Multimodal Understanding | MMBench | 26 | Jul 1, 2026 | ||
| Multi-hop Question Answering | 2WikiMultiHopQA | 26 | Jun 5, 2026 | ||
| Open-ended Dialogue Generation | CMD (test) | 26 | May 28, 2026 | ||
| Answer Accuracy | ChatDoctor | 26 | May 27, 2026 | ||
| Answer Accuracy | Samsum | 26 | May 27, 2026 | ||
| Answer Accuracy | Alpaca | 26 | May 27, 2026 | ||
| Clinical Reasoning | ER-Reason | 26 | May 27, 2026 | ||
| Clinical Reasoning | MIMIC-CDM-FI | 26 | May 27, 2026 | ||
| Clinical Reasoning | MedCaseReasoning | 26 | May 27, 2026 | ||
| Math | AIME 2025 | 26 | Jun 9, 2026 | ||
| Arithmetic Reasoning | Average Arithmetic Reasoning Tasks | 26 | May 27, 2026 | ||
| Image Classification | Classification Suite (OxfordPets, EuroSAT, Caltech101, DTD, FGVCAircraft, Flowers102, UCF101, Food101, SUN397, StanfordCars, Imagenet) Few-shot CLIP RN50 pre-trained (test) | 26 | May 27, 2026 | ||
| Text-to-Image Generation | DrawBench | 26 | Jun 30, 2026 | ||
| Mathematical Reasoning | Olympiad | 26 | Jun 24, 2026 |