Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 705 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instruction Following | Evol-Inst | 34 | May 7, 2026 | ||
| Anomaly Detection | TSB-AD U | 34 | Mar 5, 2026 | ||
| Multimodal Search | BrowseComp-VL | 34 | Jun 16, 2026 | ||
| Multimodal Safety Evaluation | MM-SafetyBench | 34 | Jun 25, 2026 | ||
| Verilog Code Generation | VerilogEval SR v2 | 34 | Mar 4, 2026 | ||
| Robotic Manipulation | RMBench | 34 | Jul 7, 2026 | ||
| Low-light Image Enhancement | LOL real v2 | 34 | May 19, 2026 | ||
| AI-generated image detection | Glide | 34 | May 21, 2026 | ||
| Semantic Segmentation | Cross-Domain Average (Cityscapes, BDD100K, Mapillary) | 34 | Jul 9, 2026 | ||
| Image Classification | ImageNet-SK (test) | 34 | Feb 27, 2026 | ||
| Adversarial Robustness | ImageNet 1k (test) | 34 | Feb 27, 2026 | ||
| Video Retrieval | MSR-VTT | 34 | May 19, 2026 | ||
| Trajectory Prediction | NAVSIM (navtest) | 34 | Jul 3, 2026 | ||
| Image-to-Video Generation | VBench (test) | 34 | Jul 3, 2026 | ||
| Sequential Recommendation | ML-100K | 34 | May 12, 2026 | ||
| Machine Unlearning | MUSE NEWS | 34 | Jun 25, 2026 | ||
| Video Understanding | Video Understanding Suite MVBench, EgoSchema, VMME, LVB, VMMMU | 34 | Feb 26, 2026 | ||
| Image Understanding | Image Understanding Suite (TextVQA, ChartQA, MMStar, MMBench, MMVet, MME, RealWorldQA, COCO) | 34 | Feb 26, 2026 | ||
| Large Language Model Watermarking | Mistral-7B-Instruct (test) | 34 | Feb 26, 2026 | ||
| Brain Tumor Segmentation | BraTS 2020 | 34 | Jun 12, 2026 | ||
| Language Modeling | Arxiv (val) | 34 | May 26, 2026 | ||
| Image Classification | ImageNet-1k (val) | 34 | Feb 27, 2026 | ||
| Classification | myocardial | 34 | Jun 11, 2026 | ||
| Instruction Following | AlpacaEval Length-controlled | 34 | May 29, 2026 | ||
| 3D Semantic Mapping | Replica | 34 | Jun 23, 2026 |