Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1246 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Membership Inference Attack | Clinicalnotes fine-tuned (test) | 24 | Feb 26, 2026 | ||
| Rerouting Mitigation | D (test) | 24 | Feb 26, 2026 | ||
| Prompt Injection Prevention | NQ simplified | 24 | Feb 26, 2026 | ||
| Top-5 most frequently visited location querying | Foursquare check-in raw (test) | 24 | Feb 26, 2026 | ||
| Activity Prediction | Capture24 Top-3 most frequent activities | 24 | Feb 26, 2026 | ||
| Human Activity Recognition | Capture24 2024 | 24 | Feb 26, 2026 | ||
| Top-k popular visited location prediction | Foursquare check-in dataset Top-3 popular visited locations 77 most common labels | 24 | Feb 26, 2026 | ||
| Power-based Malware Detection | Power-based Malware Detection Dataset | 24 | Feb 26, 2026 | ||
| Vulnerability Detection | PrimeVul | 24 | Feb 27, 2026 | ||
| LLM Inference Acceleration | MBPP | 24 | Feb 26, 2026 | ||
| Temporal Question Answering | TransientTables (test) | 24 | Feb 26, 2026 | ||
| NLP Watermarking | WaterBench & RepoBench-P (test) | 24 | Feb 26, 2026 | ||
| Mandarin Dialect Identification | KeSpeech (test) | 24 | Feb 26, 2026 | ||
| GUI reasoning | AndroidControl Low | 24 | Apr 16, 2026 | ||
| Question Answering | GPQA | 24 | Feb 26, 2026 | ||
| Summarization | Aggregate (test) | 24 | Feb 26, 2026 | ||
| Summarization | SciGen (test) | 24 | Feb 26, 2026 | ||
| Summarization | BookSum (test) | 24 | Feb 26, 2026 | ||
| Summarization | ArXiv (test) | 24 | Feb 26, 2026 | ||
| Machine Reading Comprehension | Belebele Target language | 24 | Mar 24, 2026 | ||
| Multimodal Reasoning | NaturalBench | 24 | Feb 26, 2026 | ||
| Physical Commonsense Reasoning | PIQA | 24 | Feb 26, 2026 | ||
| Boolean Question Answering | BoolQ | 24 | Feb 26, 2026 | ||
| Paraphrase Detection | MRPC | 24 | Feb 26, 2026 | ||
| Sentiment Classification | SST-2 | 24 | Feb 26, 2026 |