Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1686 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Regression | Squirrel | 20 | Feb 26, 2026 | ||
| Node Regression | Crocodile | 20 | Feb 26, 2026 | ||
| Node Regression | Chameleon | 20 | Feb 26, 2026 | ||
| Biomedical Entity Linking | COMETA | 20 | Feb 26, 2026 | ||
| Biomedical Entity Linking | NCBI | 20 | Feb 26, 2026 | ||
| Aspect-Based Sentiment Analysis (ABSA) | ACOS Rest | 20 | Feb 26, 2026 | ||
| Emotion Recognition | DFEW (test) | 20 | Feb 26, 2026 | ||
| Knowledge Base Question Answering | WebQSP → GraphQA-Pop (test) | 20 | Feb 26, 2026 | ||
| Surgical Phase Recognition | Cataract-101 | 20 | May 15, 2026 | ||
| Dichotomous Image Segmentation | DIS5K TE4 (test) | 20 | May 15, 2026 | ||
| Dichotomous Image Segmentation | DIS5K TE3 (test) | 20 | May 15, 2026 | ||
| Dichotomous Image Segmentation | DIS5K TE2 (test) | 20 | May 15, 2026 | ||
| Dichotomous Image Segmentation | DIS5K TE1 (test) | 20 | May 15, 2026 | ||
| Interleaved Image-Text Generation | RISEBench | 20 | Mar 31, 2026 | ||
| Process Reward Model Assessment | PROCESSBENCH | 20 | Apr 28, 2026 | ||
| Alignment | UltraFeedback (test) | 20 | Jun 2, 2026 | ||
| tracking shuffled objects seven objects | BBH (test) | 20 | May 21, 2026 | ||
| Text-to-motion generation | HumanML3D full dimension (test) | 20 | Feb 26, 2026 | ||
| End-to-end Question Answering | MultiHopRAG (test val) | 20 | Feb 26, 2026 | ||
| End-to-end Question Answering | MuSiQue (test val) | 20 | Feb 26, 2026 | ||
| End-to-end Question Answering | 2WikiMultiHopQA (test val) | 20 | Feb 26, 2026 | ||
| End-to-end Question Answering | HotpotQA (test val) | 20 | Feb 26, 2026 | ||
| Sequence Labeling | Restaurant 16 | 20 | Feb 26, 2026 | ||
| Sequence Labeling | Restaurant15 | 20 | Feb 26, 2026 | ||
| Sequence Labeling | Restaurant 14 | 20 | Feb 26, 2026 |