Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 589 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME 2024 (held-out) | 38 | Jun 16, 2026 | ||
| Closed-loop planning | NAVSIM v1 (test) | 38 | Jul 7, 2026 | ||
| Language Modeling | (val) | 38 | May 12, 2026 | ||
| Image Reconstruction | ImageNet 256p | 38 | May 14, 2026 | ||
| Large Language Model Evaluation | Qwen3-0.6B Average (test) | 38 | May 7, 2026 | ||
| LLM Evaluation | Qwen3-1.7B Evaluation Suite (avg) | 38 | May 7, 2026 | ||
| Object Classification | ScanObjectNN OBJ_ONLY variant | 38 | Jul 8, 2026 | ||
| Object Classification | ScanObjectNN OBJ_BG variant | 38 | Jul 8, 2026 | ||
| GUI grounding | UI-Vision | 38 | Jun 30, 2026 | ||
| Medical Time Series Classification | PTB-XL 5-Classes | 38 | May 22, 2026 | ||
| Medical Time Series Classification | ADFTD 3-Classes | 38 | May 22, 2026 | ||
| Spatial Understanding | EmbSpatial | 38 | Jul 2, 2026 | ||
| Class Incremental Learning | CIFAR100 20-Split | 38 | Apr 29, 2026 | ||
| Chart-to-code generation | ChartMimic Chart2Python (test) | 38 | Apr 28, 2026 | ||
| Question Answering | MultiFieldQA en | 38 | Apr 28, 2026 | ||
| Question Answering | NarrativeQA | 38 | Apr 28, 2026 | ||
| Embodied Instruction Following | AlfWorld | 38 | Jun 4, 2026 | ||
| Lesion Segmentation | HAM10000 | 38 | Jun 30, 2026 | ||
| Psychometric Predictive Power | SAP ROI | 38 | Apr 21, 2026 | ||
| Multimodal Mathematical Reasoning | FlowVerse Text Centric | 38 | Apr 21, 2026 | ||
| Out-of-Distribution Detection | CIFAR 100 Near OOD | 38 | May 28, 2026 | ||
| Mathematical Reasoning | AIME | 38 | Apr 20, 2026 | ||
| Mathematical Reasoning | AMC23 | 38 | May 29, 2026 | ||
| Object Hallucination evaluation | POPE (average across random and popular) | 38 | Apr 29, 2026 | ||
| Long-form generation | Long-form generation ID | 38 | Apr 14, 2026 |