Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 866 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Model Fingerprinting | Pruning Positive Samples | 30 | Feb 26, 2026 | ||
| Model Fingerprinting | RL Positive Samples | 30 | Feb 26, 2026 | ||
| Model Fingerprinting | Multi Modal Positive Samples | 30 | Feb 26, 2026 | ||
| Model Fingerprinting | Upcycling Positive Samples | 30 | Feb 26, 2026 | ||
| Model Fingerprinting | Continual Pretrain Positive Samples | 30 | Feb 26, 2026 | ||
| Model Fingerprinting | SFT Positive Samples | 30 | Feb 26, 2026 | ||
| Zero-shot Language Modeling | LM Evaluation Harness 0-shot | 30 | Feb 26, 2026 | ||
| Mathematical Reasoning | Olympiad Bench | 30 | May 13, 2026 | ||
| Object Goal Navigation | MP3D 1.0 (val) | 30 | Jun 2, 2026 | ||
| Segmentation | Liver tumour | 30 | Feb 26, 2026 | ||
| Segmentation | Lung tumour | 30 | Feb 26, 2026 | ||
| Adversarial Defense | CIFAR-10 (test) | 30 | May 27, 2026 | ||
| General Reasoning | Average of Reasoning Tasks | 30 | May 19, 2026 | ||
| Summarization | SAMSum Full 2019 | 30 | Feb 26, 2026 | ||
| Question Answering | MuSiQuest-E 2022 (Full) | 30 | Feb 26, 2026 | ||
| Question Answering | QASPER-E 2021 (Full) | 30 | Feb 26, 2026 | ||
| Question Answering | HotpotQA-E 2018 (Full) | 30 | Feb 26, 2026 | ||
| Time Series Forecasting | dominick | 30 | May 12, 2026 | ||
| Mathematical multi-modal reasoning | WeMath | 30 | May 13, 2026 | ||
| Multi-objective Optimization | ZINC-250k (logP-TPSA) | 30 | Feb 26, 2026 | ||
| Molecular property optimization | ZINC-250k | 30 | Feb 26, 2026 | ||
| Portfolio Optimization | S&P 500 constituents (test) | 30 | Feb 26, 2026 | ||
| Two-sample testing | Expo-1D | 30 | Feb 26, 2026 | ||
| Pronunciation Assessment | Speechocean762 (test) | 30 | Jun 19, 2026 | ||
| Audio Classification | US8K | 30 | Jun 16, 2026 |