Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1472 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Forecasting | Traffic | 21 | Mar 5, 2026 | ||
| Time Series Forecasting | Electricity | 21 | Mar 5, 2026 | ||
| Time Series Forecasting | ETTm2 | 21 | Mar 5, 2026 | ||
| Time Series Forecasting | ETTm1 | 21 | Mar 5, 2026 | ||
| Time Series Forecasting | ETTh2 | 21 | Mar 5, 2026 | ||
| Multimodal Understanding | MMBench EN v1.1 (dev) | 21 | May 19, 2026 | ||
| Single-Step Retrosynthesis | URSA expert 2026 | 21 | Mar 5, 2026 | ||
| Video Generation | VideoPhy2 (test) | 21 | May 26, 2026 | ||
| Asymmetric Capacitated Vehicle Routing Problem | ACVRP1000 generalization | 21 | Jun 2, 2026 | ||
| Clean table | Real-world | 21 | Jun 8, 2026 | ||
| Audio Understanding | MMAU mini original (test) | 21 | Mar 4, 2026 | ||
| Mathematical Reasoning | gsm8k cot | 21 | May 12, 2026 | ||
| Text-to-Video Generation | VBench | 21 | Mar 4, 2026 | ||
| Text-to-Image Generation | MS-COCO | 21 | Jun 2, 2026 | ||
| Parallel Code Generation | ParEval | 21 | Mar 4, 2026 | ||
| RGB-Thermal Tracking | LasHeR | 21 | May 6, 2026 | ||
| Mathematical Reasoning | GSM8K Qwen2.5-Instruct (test) | 21 | Mar 4, 2026 | ||
| Robot Manipulation | MetaWorld (12 unseen tasks) | 21 | Mar 4, 2026 | ||
| Associative Retrieval | Balanced Random Patterns flip noise | 21 | Mar 4, 2026 | ||
| Mathematical Problem Solving | AIME 2024 | 21 | Apr 1, 2026 | ||
| Class-incremental learning | FG-ImageNet | 21 | Mar 4, 2026 | ||
| Class-incremental learning | Mini-ImageNet | 21 | Mar 4, 2026 | ||
| Aspect-Sentiment-Query-Pair Extraction | Rest 16 | 21 | Mar 4, 2026 | ||
| Aspect-Sentiment-Query-Pair Extraction | Rest15 | 21 | Mar 4, 2026 | ||
| Model Editing | ZSRE sequential editing of 1000 facts | 21 | Mar 4, 2026 |