Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2686 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-context language understanding | LongBench Ministral-8B-Instruct | 14 | Apr 10, 2026 | ||
| Long-context Understanding | LongBench LLaMA-3.1-8B-Instruct (test) | 14 | Apr 10, 2026 | ||
| Image Classification | Tiny-ImageNet | 14 | Apr 10, 2026 | ||
| Classification Calibration | AV1451 | 14 | Apr 10, 2026 | ||
| Reaction Prediction | ChemRxn-VP | 14 | Apr 10, 2026 | ||
| Reaction Recognition | ChemRxn-VR | 14 | Apr 10, 2026 | ||
| Molecular Recognition | img2smiles | 14 | Apr 10, 2026 | ||
| Molecular Recognition | MMChemOCR | 14 | Apr 10, 2026 | ||
| Length of Stay (LOS) Prediction | MIMIC-III (test) | 14 | Apr 21, 2026 | ||
| Mortality Prediction | MIMIC-III (test) | 14 | Apr 10, 2026 | ||
| Multi-task Language Understanding | MMLU | 14 | Apr 9, 2026 | ||
| Image Compression | Kodak | 14 | Jun 23, 2026 | ||
| Computational Efficiency | Malicious Prompt Detection Benchmarks | 14 | Apr 9, 2026 | ||
| Multimodal Understanding | MMBench OOD | 14 | Apr 9, 2026 | ||
| Multimodal Understanding | MM-Vet OOD | 14 | Apr 9, 2026 | ||
| Multimodal Understanding | CC3M IOD | 14 | Apr 9, 2026 | ||
| Multimodal Understanding | GPT4V-Caption (IOD) | 14 | Apr 9, 2026 | ||
| Malicious Prompt Detection | MMBench OOD | 14 | Apr 9, 2026 | ||
| Malicious Prompt Detection | MM-Vet OOD | 14 | Apr 9, 2026 | ||
| Malicious Prompt Detection | CC3M (IOD) | 14 | Apr 9, 2026 | ||
| Malicious Prompt Detection | GPT4V-Caption (IOD) | 14 | Apr 9, 2026 | ||
| Mathematical Reasoning | MATH 500 | 14 | Apr 9, 2026 | ||
| Mathematical Reasoning | GSM8K | 14 | Apr 9, 2026 | ||
| Speech Translation | CoVost2 en2zh | 14 | Apr 9, 2026 | ||
| UI Element Grounding | ScreenSpot Overall v2 (Aggregated) | 14 | Apr 9, 2026 |