Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 269 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dimensionality Reduction | Cassin's | 63 | Feb 26, 2026 | ||
| 1D audio reconstruction | AudioSet | 63 | Feb 26, 2026 | ||
| Tucker decomposition | Cardiac MRI tensor | 63 | Feb 26, 2026 | ||
| Multimodal Understanding | MMB | 63 | Jun 16, 2026 | ||
| Referring Image Segmentation | RefCOCOg (test(U)) | 63 | Jun 23, 2026 | ||
| Referring Image Segmentation | RefCOCOg (val (U)) | 63 | Jun 23, 2026 | ||
| Multimodal Understanding | MMBench EN v1.1 | 63 | May 1, 2026 | ||
| Video Object Segmentation | LVOS v2 (val) | 63 | May 19, 2026 | ||
| Robotic Manipulation | RLBench | 63 | May 7, 2026 | ||
| Scene Classification | RESISC-45 (TR=10%) | 63 | May 12, 2026 | ||
| Financial Safety Evaluation | FinRED R5: Compliance Evasion | 62 | Jun 19, 2026 | ||
| Financial Safety Evaluation | FinRED R4: Consumer Rights | 62 | Jun 19, 2026 | ||
| Financial Safety Evaluation | FinRED R3: Misinformation | 62 | Jun 19, 2026 | ||
| Financial Safety Evaluation | FinRED R2: Financial Crime | 62 | Jun 19, 2026 | ||
| Financial Safety Evaluation | FinRED R1: Cyber Threats | 62 | Jun 19, 2026 | ||
| Retrieval | HotPotQA | 62 | Jun 12, 2026 | ||
| Planning | NAVSIM v1 (test) | 62 | Jun 16, 2026 | ||
| Jailbreak Attack Success | STRONGREJECT (train) | 62 | Jun 4, 2026 | ||
| Jailbreaking Attack Success | STRONGREJECT 40 held-out behaviors | 62 | Jun 4, 2026 | ||
| Jailbreak Robustness | STRONGREJECT (train) | 62 | Jun 4, 2026 | ||
| Jailbreak Attack Success | STRONGREJECT 60 behaviors (train) | 62 | Jun 4, 2026 | ||
| Image Classification | ImageNet 1k | 62 | Jul 7, 2026 | ||
| Text-to-Image Retrieval | MIRFlickr | 62 | Jun 2, 2026 | ||
| Image-to-Text Retrieval | NUS-WIDE | 62 | Jun 2, 2026 | ||
| Image-to-Text Retrieval | MIRFlickr | 62 | Jun 2, 2026 |