Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1193 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| ECG Classification | ZZU pECG (test) | 24 | May 11, 2026 | ||
| Safety Guardrailing | ULSPB 350 interaction runs | 24 | May 11, 2026 | ||
| Embedding Reconstruction | CLIP vision embeddings CC3M and ImageNet | 24 | May 8, 2026 | ||
| Minimize transmit power with SINR and SIC constraints | Full Duplex QAM Scenario 05 | 24 | May 8, 2026 | ||
| Maximize minimum secrecy rate with eavesdropper constraints | Cognitive Radio multicast secrecy Scenario 04 | 24 | May 8, 2026 | ||
| Mathematical Reasoning | SVAMP | 24 | May 8, 2026 | ||
| Mathematical Reasoning | GSM8k Hard | 24 | May 8, 2026 | ||
| Mathematical Reasoning | GSM8k | 24 | May 8, 2026 | ||
| Feature Attribution | ImageNet 1000 samples (val) | 24 | May 8, 2026 | ||
| Automated profiling audit | Academic records profiling dataset | 24 | May 8, 2026 | ||
| Robot Manipulation | Google Robot variant evaluation SimplerEnv | 24 | May 8, 2026 | ||
| Visual Information Seeking | InfoSeek | 24 | May 7, 2026 | ||
| Web-search QA | BrowseComp-VL | 24 | May 7, 2026 | ||
| Multimodal Question Answering | LiveVQA | 24 | May 7, 2026 | ||
| Web-search QA | VDR | 24 | May 7, 2026 | ||
| Hallucination Detection | TriviaQA n=1000 (test) | 24 | May 7, 2026 | ||
| Hallucination Detection | PopQA n=1000 (test) | 24 | May 7, 2026 | ||
| Tool Use | tool-use (test) | 24 | May 7, 2026 | ||
| Hallucination Detection | MedHallu | 24 | May 19, 2026 | ||
| Medical Image Classification | Harvard-FairVLMed Linear Probing (test) | 24 | May 7, 2026 | ||
| Binary classification | Creditcard | 24 | Jun 17, 2026 | ||
| Binary classification | Jasmine | 24 | Jun 17, 2026 | ||
| Binary classification | OVA Uterus | 24 | Jun 17, 2026 | ||
| Code Generation | HumanEval | 24 | May 7, 2026 | ||
| Science Reasoning | GPQA | 24 | May 7, 2026 |