Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2249 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Code Generation | MBPP | 16 | Feb 26, 2026 | ||
| Mathematical problem solving | MATH 519 problems (test) | 16 | Feb 26, 2026 | ||
| Prompt Injection | MMLU random topology | 16 | May 19, 2026 | ||
| Tool Attack Defense | InjecAgent random topology (test) | 16 | Feb 26, 2026 | ||
| Prompt Injection Defense | CSQA | 16 | Feb 26, 2026 | ||
| Prompt Injection Defense | PI (CSQA) random topology | 16 | Feb 26, 2026 | ||
| Prompt Injection Defense | GSM8K PI (Prompt Injection) (test) | 16 | Feb 26, 2026 | ||
| indirect reciprocity game | finite-horizon indirect reciprocity game | 16 | Feb 26, 2026 | ||
| Spatial Prediction | SRTM N43W080 (test) | 16 | Feb 26, 2026 | ||
| Spatial Prediction | SRTM N37W120 (test) | 16 | Feb 26, 2026 | ||
| Spatial Prediction | SRTM N39W106 (test) | 16 | Feb 26, 2026 | ||
| Class-Incremental Learning | ImageNet-R N = 10 | 16 | Mar 13, 2026 | ||
| Natural Language Understanding | GLUE standard (test val) | 16 | May 15, 2026 | ||
| Natural Language Understanding | GLUE RoBERTa-base (val) | 16 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE | 16 | Feb 26, 2026 | ||
| Disposition after emergency department visit (ED dispo) | MC-MED | 16 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Ant kinematic shifts | 16 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Walker2d kinematic shifts | 16 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Hopper kinematic shifts | 16 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah kinematic shifts | 16 | Feb 26, 2026 | ||
| Membership Inference | Video modality | 16 | Feb 26, 2026 | ||
| Regression | Trivariate-2 synthetic (test) | 16 | Feb 26, 2026 | ||
| Regression | Trivariate-1 synthetic (test) | 16 | Feb 26, 2026 | ||
| Regression | Bivariate synthetic (test) | 16 | Feb 26, 2026 | ||
| Regression | Univariate synthetic (test) | 16 | Feb 26, 2026 |