Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 129 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hyperspectral Image Classification | Indian Pines (test) | 100 | May 1, 2026 | ||
| Node Classification | Citeseer transductive (test) | 100 | Mar 16, 2026 | ||
| Text Classification | Yelp (test) | 100 | May 12, 2026 | ||
| Open-Ended Visual Question Answering | VQA 1.0 (test-dev) | 100 | Feb 26, 2026 | ||
| Image Retrieval | Oxford 5k | 100 | Feb 26, 2026 | ||
| Classification | CUB | 100 | Jun 26, 2026 | ||
| Automated Theorem Proving | MiniF2F (test) | 100 | Jun 18, 2026 | ||
| Action Recognition | NTU-120 96/24 split | 100 | Apr 21, 2026 | ||
| Visual Place Recognition | AmsterTime | 100 | May 21, 2026 | ||
| Semantic Segmentation | PASCAL 5-shot 5i | 100 | Feb 26, 2026 | ||
| KV Cache Quantization | WikiText-2 prompt 2048-token (train) | 99 | Jun 24, 2026 | ||
| Commonsense Reasoning | Six commonsense reasoning tasks zero-shot | 99 | Jul 9, 2026 | ||
| Mimicry Defense | TI-Dataset | 99 | Jun 11, 2026 | ||
| Image Retrieval | Oxford Flowers | 99 | May 19, 2026 | ||
| Physical Commonsense Reasoning | PIQA | 99 | May 29, 2026 | ||
| Anti-steganalysis | Audioset | 99 | Apr 24, 2026 | ||
| Anti-steganalysis | GTZAN | 99 | Apr 24, 2026 | ||
| Anti-steganalysis | LJSpeech | 99 | Apr 24, 2026 | ||
| Anti-steganalysis | TIMIT | 99 | Apr 24, 2026 | ||
| Variable Gapped Longest Common Subsequence Problem | RANDOM benchmark suite | 99 | Apr 23, 2026 | ||
| Planning | IPC Domains | 99 | Apr 1, 2026 | ||
| Long Video Understanding | LongVideo Bench | 99 | May 12, 2026 | ||
| Reward Modeling Evaluation | RM-Bench | 99 | Jun 9, 2026 | ||
| Math Reasoning | AMC23 | 99 | May 26, 2026 | ||
| Jailbreak Attack | Malicious goals dataset (test) | 99 | Mar 10, 2026 |