Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 848 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spatio-temporal forecasting | SDWPF (20% test) | 30 | Apr 20, 2026 | ||
| Automatic Speech Recognition | FLEURS (test) | 30 | Jul 7, 2026 | ||
| Classification | Adult Dataset | 30 | Apr 20, 2026 | ||
| Classification | Br2000 (test) | 30 | Apr 20, 2026 | ||
| Massive Multitask Language Understanding | MMLU | 30 | Apr 20, 2026 | ||
| Recommendation | Movielens | 30 | Apr 20, 2026 | ||
| Cross-view Geo-localization | SUES-200 Satellite→Drone 150m | 30 | May 12, 2026 | ||
| Continual Instruction Tuning | UCIT | 30 | Jun 2, 2026 | ||
| Agent Safety Evaluation | Agent-SafetyBench aggregated clean and five attack types | 30 | Apr 16, 2026 | ||
| Preference Prediction | JudgeBench | 30 | Jul 3, 2026 | ||
| Online Class Incremental Learning | CIFAR-100 | 30 | Apr 16, 2026 | ||
| Online Class Incremental Learning | CIFAR-10 | 30 | Apr 16, 2026 | ||
| Online Class Incremental Learning | Tiny-Imagenet (test) | 30 | Apr 16, 2026 | ||
| Online Class Incremental Learning | CIFAR-10 (test) | 30 | Apr 16, 2026 | ||
| Three-way probability ranking | COMMON2SENSE paired | 30 | Apr 15, 2026 | ||
| Global Counterfactual Explanations | Adult | 30 | Apr 15, 2026 | ||
| Node Classification | Instagram OOD (test) | 30 | Apr 15, 2026 | ||
| Node Classification | Citeseer OOD (test) | 30 | Apr 15, 2026 | ||
| Question Answering | MetaQA 1-hop | 30 | Apr 15, 2026 | ||
| Question Answering | CWQ | 30 | Jun 16, 2026 | ||
| Natural Language Understanding | GLUE | 30 | Jun 2, 2026 | ||
| Summarization | GovReport | 30 | May 11, 2026 | ||
| Mathematical Reasoning | MATH500 4-shot | 30 | Apr 20, 2026 | ||
| General Capability | BBH, GSM8K, MMLU, TruthfulQA, HumanEval, MBPP | 30 | Apr 14, 2026 | ||
| Knowledge | MMLU, TruthfulQA | 30 | Apr 14, 2026 |