Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 341 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Attack | SafeBench | 54 | Mar 10, 2026 | ||
| Jailbreak Defense | StrongReject | 54 | Apr 14, 2026 | ||
| Forecasting | Weather | 54 | Jul 3, 2026 | ||
| Citation Attributability | Transfer | 54 | Mar 5, 2026 | ||
| Citation Control | CITECONTROL | 54 | Mar 5, 2026 | ||
| Medical Diagnosis | MIMIC-IV diagnostic evaluation set (test) | 54 | Mar 4, 2026 | ||
| Verilog Code Generation | VerilogEval v1 (Human) | 54 | Apr 13, 2026 | ||
| Seizure Forecasting | CHB-MIT Scalp EEG | 54 | Mar 4, 2026 | ||
| GUI State Control | State Control Benchmark | 54 | Mar 4, 2026 | ||
| OOD Detection | CIFAR-10 Average OOD ID (test) | 54 | Jul 8, 2026 | ||
| Single-class Unlearning | CIFAR-10 | 54 | Jun 17, 2026 | ||
| Scene Text Recognition | Union14M Benchmark | 54 | Jun 24, 2026 | ||
| Molecular Property Prediction (Regression) | Lipophilicity | 54 | Jul 9, 2026 | ||
| Question Answering | TruthfulQA MC1 | 54 | Mar 16, 2026 | ||
| Long-context Question Answering | 2WikiMultiHopQA (Out-Of-Distribution) | 54 | Feb 26, 2026 | ||
| Class-to-image generation | ImageNet | 54 | Jun 16, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo halfcheetah-medium-expert | 54 | Jun 11, 2026 | ||
| Image Classification | CIFAR-10 clean (test) | 54 | Jul 7, 2026 | ||
| Class-Incremental Learning | VTAB B0 Inc10 | 54 | May 29, 2026 | ||
| Concept leakage evaluation | CUB | 54 | Feb 26, 2026 | ||
| Verification | Bitcoin Simulation | 54 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 25 | 54 | Mar 24, 2026 | ||
| Biclustering | Simulated dataset (val) | 54 | Feb 26, 2026 | ||
| Biclustering | Simulated dataset (train) | 54 | Feb 26, 2026 | ||
| Fetal Head Segmentation | HC18 | 54 | Jun 16, 2026 |