Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1295 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Scaling Law Fitting | LLM-github (test) | 23 | May 19, 2026 | ||
| Scaling Law Fitting | LLM-commoncrawl (test) | 23 | May 19, 2026 | ||
| Scaling Law Fitting | LLM-c4 (test) | 23 | May 19, 2026 | ||
| Scaling Law Fitting | LLM-book (test) | 23 | May 19, 2026 | ||
| Scaling Law Fitting | LLM-arxiv (test) | 23 | May 19, 2026 | ||
| Indicator Retrieval | BacktestBench synthetic (test) | 23 | May 19, 2026 | ||
| SQL Generation | BacktestBench synthetic (test) | 23 | May 19, 2026 | ||
| Financial Backtesting Accuracy | BacktestBench synthetic (test) | 23 | May 19, 2026 | ||
| Knowledge Retrieval | KGFACT RETRIEVAL | 23 | May 19, 2026 | ||
| Automated Planning | IPC 2023 (test) | 23 | May 29, 2026 | ||
| Image Super-Resolution | DRealSR | 23 | May 25, 2026 | ||
| Cross-domain Sequential Recommendation | Amazon Kitchen (test) | 23 | Jun 11, 2026 | ||
| Cross-domain Sequential Recommendation | Amazon Food (test) | 23 | Jun 11, 2026 | ||
| Visual Question Answering | GranuVistaVQA | 23 | May 15, 2026 | ||
| Organizational target classification | Hacker Forum Exploit Posts OOD 2024+ (test) | 23 | May 15, 2026 | ||
| Synthetic Image Detection | Synthbuster | 23 | May 26, 2026 | ||
| 3D Object Detection | nuScenes (val) | 23 | Jul 2, 2026 | ||
| Class-Incremental Learning | ImageNet-R B0 Inc20 (test) | 23 | May 29, 2026 | ||
| Image Reconstruction | OmniDoc-TokenBench 256x256 (test) | 23 | May 14, 2026 | ||
| Interactive Desktop Task Success | OSWorld | 23 | Jun 24, 2026 | ||
| Semantic Segmentation | YCB-V | 23 | May 26, 2026 | ||
| Single-Source Shortest Path Prediction | ECHO-Synth | 23 | May 19, 2026 | ||
| Node Eccentricity Prediction | ECHO-Synth | 23 | May 19, 2026 | ||
| Diameter Prediction | ECHO-Synth | 23 | May 19, 2026 | ||
| Open-set Point Cloud Semantic Segmentation | S3DIS Manual-10-3 | 23 | May 13, 2026 |