Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1351 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Speculative Decoding | Med | 22 | May 28, 2026 | ||
| Speculative Decoding | Law | 22 | May 28, 2026 | ||
| Speculative Decoding | Code | 22 | May 28, 2026 | ||
| Multi-domain Task-Incremental Learning | Aircraft, Caltech101, CIFAR100, DTD, EuroSAT, Flowers, Food, MNIST, OxfordPet, Cars, SUN397 (MTIL suite) 5-shot 1.0 (test) | 22 | May 28, 2026 | ||
| Mathematical Reasoning | GSM+ | 22 | Jun 24, 2026 | ||
| Tax Evasion Detection | T20H | 22 | May 27, 2026 | ||
| Prompt Watermarking and Verification | OxfordPets | 22 | May 27, 2026 | ||
| Prompt Watermarking and Verification | Caltech101 | 22 | May 27, 2026 | ||
| Prompt Watermarking and Verification | ImageNet | 22 | May 27, 2026 | ||
| Value Alignment | Confucianism-4 | 22 | May 27, 2026 | ||
| Negotiation | CRAD | 22 | May 27, 2026 | ||
| Mean Deviation prediction | In-house (test) | 22 | May 27, 2026 | ||
| Mean Deviation prediction | STAGE2 (test) | 22 | May 27, 2026 | ||
| Dynamic Agent Security and Utility Evaluation | AgentDyn | 22 | May 27, 2026 | ||
| Agentic Security and Utility Evaluation | AgentDojo | 22 | May 27, 2026 | ||
| Anomaly Detection | Dataset 2 (test) | 22 | May 27, 2026 | ||
| Anomaly detection | IC Parametric 1 (test) | 22 | May 27, 2026 | ||
| Text-to-Image Generation | MSCOCO 10k (val) | 22 | May 27, 2026 | ||
| Math | GSM8K | 22 | Jun 16, 2026 | ||
| 3D Medical Image Segmentation | Pancreas-CT 20% labeled | 22 | May 26, 2026 | ||
| Metaphorical Video Understanding | MetaphorVU-Bench | 22 | May 26, 2026 | ||
| Time-series Imputation | ETT (Original In-Sample) | 22 | May 26, 2026 | ||
| Time-series Imputation | ETT Original (Out-of-Sample) | 22 | May 26, 2026 | ||
| Toxicity prediction | TransLipid (test) | 22 | May 26, 2026 | ||
| Forecasting | ETTh1 | 22 | Jun 2, 2026 |