Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1377 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Safety Evaluation | MSSBench | 22 | Mar 4, 2026 | ||
| Multimodal Safety Evaluation | BeaverTails-V | 22 | Mar 4, 2026 | ||
| General Visual Reasoning | MMMU | 22 | Jun 1, 2026 | ||
| Multi-choice Medical Question Answering | Medical QA Multi-choice | 22 | Mar 4, 2026 | ||
| Medical Reasoning | MedDDx | 22 | Mar 4, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 22 | Mar 4, 2026 | ||
| Regression | superconductor | 22 | Mar 4, 2026 | ||
| Regression | parkinsons | 22 | Mar 4, 2026 | ||
| Regression | kin8nm | 22 | Mar 4, 2026 | ||
| Regression | allstate | 22 | Mar 4, 2026 | ||
| Solitaire Solvability Estimation | Solitaire and Patience Games (various) | 22 | Mar 4, 2026 | ||
| Document Visual Question Answering | InfographicVQA | 22 | Mar 4, 2026 | ||
| Micro-video recommendation | Microlens small (test) | 22 | Mar 4, 2026 | ||
| Fluency Assessment | WMDP | 22 | Mar 4, 2026 | ||
| Image Classification | ImageNette Long-tailed ImageNet | 22 | Mar 4, 2026 | ||
| Image Classification | ImageWoof Long-tailed ImageNet Subset | 22 | Mar 4, 2026 | ||
| Image Classification | ImageSquawk Long-tailed ImageNet | 22 | Mar 4, 2026 | ||
| Image Classification | ImageMeow Long-tailed ImageNet | 22 | Mar 4, 2026 | ||
| Multi-organ Segmentation | BTCV | 22 | Mar 4, 2026 | ||
| Language Modeling | C4 Llama-3.1-8B-Instruct (val) | 22 | Mar 4, 2026 | ||
| Language Modeling | WikiText-2 Llama-3.1-8B-Instruct (test) | 22 | Mar 4, 2026 | ||
| LLM-as-a-Judge Evaluation | JudgeBench (test) | 22 | Mar 4, 2026 | ||
| Reward Modeling | RMB (test) | 22 | Mar 4, 2026 | ||
| Multivariate Time Series Classification | MotorImagery UEA (test) | 22 | Apr 23, 2026 | ||
| Multivariate Time Series Classification | Heartbeat UEA (test) | 22 | Apr 23, 2026 |