Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1110 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Logical Reasoning | RP LP Domain, Npred ≤ 60, δ ≤ 6 | 25 | May 7, 2026 | ||
| Logical Reasoning | RP LP Domain, Npred ≤ 30, 6 < δ ≤ 12 | 25 | May 7, 2026 | ||
| Information Extraction | 1,000-note gold-standard set 1.0 (test) | 25 | May 7, 2026 | ||
| multivariate-to-univariate forecasting | ECL | 25 | May 6, 2026 | ||
| multivariate-to-univariate forecasting | ETTm2 | 25 | May 6, 2026 | ||
| Visual Question Answering | VizWiz | 25 | May 4, 2026 | ||
| Novel View Synthesis | MatrixCity | 25 | Jul 7, 2026 | ||
| LLM Alignment | AlpacaEval 2.0 | 25 | May 19, 2026 | ||
| Dependence Detection | Linear dependence model | 25 | Apr 30, 2026 | ||
| Field-level Extraction | Private KYC Dataset | 25 | Apr 30, 2026 | ||
| Classification | Adult | 25 | Apr 30, 2026 | ||
| Long-context language understanding | Longbench | 25 | Apr 30, 2026 | ||
| Video Understanding | MVBench zero-shot | 25 | May 19, 2026 | ||
| Autonomous Driving (Perception, Prediction & Planning) | MME-RealWorld | 25 | Jul 7, 2026 | ||
| Counterfactual Prediction | Synthetic Dynamic Simulation Data | 25 | Apr 28, 2026 | ||
| Whole Slide Image Classification | PANDA | 25 | May 7, 2026 | ||
| Semantic Communication Backdoor Attack | MNIST standard (test) | 25 | Apr 28, 2026 | ||
| Backdoor Attack | ImageNet | 25 | Apr 28, 2026 | ||
| Backdoor Attack | CIFAR-10 | 25 | Apr 28, 2026 | ||
| Backdoor Attack | F-MNIST | 25 | Apr 28, 2026 | ||
| Backdoor Attack | MNIST | 25 | Apr 28, 2026 | ||
| Side-Channel Attack | HW-AES-T (holdout) | 25 | Apr 28, 2026 | ||
| COVID-19 prediction | Birmingham NHS cohort 0.8% prevalence (test) | 25 | Apr 24, 2026 | ||
| COVID-19 prediction | Birmingham 0.8% prevalence | 25 | Apr 24, 2026 | ||
| COVID-19 prediction | Oxford 1.7% prevalence | 25 | Apr 24, 2026 |