Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 861 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment Analysis | SST5 | 30 | Mar 5, 2026 | ||
| Hate Speech Detection | TE-Hate | 30 | Mar 5, 2026 | ||
| Emotion Classification | TE-Emo | 30 | Mar 5, 2026 | ||
| Sentiment Analysis | RT | 30 | Mar 5, 2026 | ||
| Text Classification | TE-Hate | 30 | Mar 5, 2026 | ||
| Text Classification | TE-Emo | 30 | Mar 5, 2026 | ||
| Text Classification | AG's News | 30 | Apr 21, 2026 | ||
| Reward Modeling | RewardBench 2 | 30 | Mar 5, 2026 | ||
| Classification | HAM10000 | 30 | Jun 30, 2026 | ||
| Indoor Semantic Segmentation | ScanNet (val) | 30 | Apr 23, 2026 | ||
| Mathematical Problem Solving | Code2Math | 30 | Mar 4, 2026 | ||
| Action Prediction | DriveAction | 30 | Jul 7, 2026 | ||
| Tool-integrated Reasoning | Computational and Knowledge-Intensive Reasoning Tasks (AIME24, AIME25, MATH500, GSM8K, MATH, WebWalker, HQA, 2Wiki., MuSiQ., Bamb.) latest (test) | 30 | Mar 4, 2026 | ||
| Tensor Decomposition | Synthetic Data (Tucker) | 30 | Mar 4, 2026 | ||
| OOD Detection | OpenOOD Far-OOD CIFAR10 | 30 | May 27, 2026 | ||
| JPEG compression artifacts removal | Urban100 | 30 | Mar 4, 2026 | ||
| Classical Image Super-Resolution | Manga109 106 (test) | 30 | Mar 4, 2026 | ||
| Classical Image Super-Resolution | Urban100 105 (test) | 30 | Mar 4, 2026 | ||
| Classical Image Super-Resolution | BSD100 104 (test) | 30 | Mar 4, 2026 | ||
| Classical Image Super-Resolution | Set14 51 (test) | 30 | Mar 4, 2026 | ||
| Classical Image Super-Resolution | Set5 103 (test) | 30 | Mar 4, 2026 | ||
| Red-teaming | 50 harmful goals (Manual evaluation) | 30 | Mar 4, 2026 | ||
| Response Moderation | Public Benchmarks for Response Moderation (SafeRLHF, WildGuard, HarmBench, BeaverTails, XSTest, Aegis 2.0) | 30 | Apr 7, 2026 | ||
| Machine Translation | Multi30K eng → fra 2017 (test) | 30 | Jun 16, 2026 | ||
| Zero-shot Language Modeling and Reasoning | MMLU-CoT, GSM8k, HellaSwag, WinoGrande zero-shot Llama-3.1-8B-Instruct | 30 | Mar 4, 2026 |