Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2579 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| CAD reconstruction from point clouds | Fusion360 (test) | 15 | Jun 4, 2026 | ||
| Single-hop Question Answering | Natural Questions | 15 | Feb 26, 2026 | ||
| Continual Instruction Following | VirtualHome | 15 | Feb 26, 2026 | ||
| Medical Image Segmentation | UDIAT | 15 | Feb 26, 2026 | ||
| Fine-grained classification | DTD (test) | 15 | May 1, 2026 | ||
| Retinal Image Registration | FIRE (test) | 15 | Feb 26, 2026 | ||
| Point Cloud Completion | KITTI-360 | 15 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Antmaze umaze-diverse | 15 | Feb 26, 2026 | ||
| Action Detection | UCF-101-24 (test) | 15 | Feb 27, 2026 | ||
| Solution Simulation | Student_15 v1.0 (test) | 15 | Feb 26, 2026 | ||
| Anomaly Classification | BUSI | 15 | Feb 26, 2026 | ||
| Biomedical Entity Linking | AAP | 15 | Feb 26, 2026 | ||
| Biomedical Entity Linking | BC5CDR | 15 | Feb 26, 2026 | ||
| Language Understanding | MMLU French (test) | 15 | Feb 26, 2026 | ||
| Science Question Answering | ARC-C French (test) | 15 | Feb 26, 2026 | ||
| Language Understanding | MMLU German (test) | 15 | Feb 26, 2026 | ||
| Science Question Answering | ARC-C German (test) | 15 | Feb 26, 2026 | ||
| Text Generation | C4 | 15 | Feb 26, 2026 | ||
| Table Question Answering | TAT-QA (test) | 15 | Feb 26, 2026 | ||
| Salient Object Detection | HRSOD 400 (test) | 15 | Feb 26, 2026 | ||
| World Knowledge and Reading Comprehension | LM Evaluation Harness NQ, MMLU STEM, ARC, SciQ, LogiQA, BoolQ | 15 | Feb 26, 2026 | ||
| Natural Language to STL Transformation | DeepSTL | 15 | May 8, 2026 | ||
| Surgical Phase Recognition | BernBypass | 15 | Feb 26, 2026 | ||
| Surgical Phase Recognition | StrasBypass | 15 | Feb 26, 2026 | ||
| Safety | 8 jailbreak attacks (Aggregated) | 15 | Feb 26, 2026 |