Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1446 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | GSM8K | 21 | May 12, 2026 | ||
| Mathematical Reasoning | MATH 500 | 21 | May 12, 2026 | ||
| Causal Discovery | Alarm d=37 | 21 | Jun 4, 2026 | ||
| Image Classification | CIFAR-10 (val) | 21 | Jun 2, 2026 | ||
| Code Generation | MBPP 3-shot | 21 | May 12, 2026 | ||
| Mathematical Reasoning | Minerva Math 4-shot | 21 | May 12, 2026 | ||
| Code Generation | Human Eval zero-shot | 21 | May 12, 2026 | ||
| Reliability prediction | POPE Adversarial | 21 | May 12, 2026 | ||
| Temporal Localization | Looting Event Localization Dataset (test) | 21 | May 12, 2026 | ||
| Month-level change detection | Afghanistan archaeological sites (test) | 21 | May 12, 2026 | ||
| Tool-agent-user interaction | TAC (TheAgentCompany) | 21 | May 11, 2026 | ||
| Math Reasoning | MATH 500 | 21 | May 11, 2026 | ||
| Algorithmic Recourse | German (10-fold cross-validation) | 21 | May 11, 2026 | ||
| Algorithmic Recourse | Attrition (10-fold cross-validation) | 21 | May 11, 2026 | ||
| Algorithmic Recourse | Attrition | 21 | May 11, 2026 | ||
| General Reasoning | Out-of-Domain Generalization Suite BGQA, CRUX, STGQA, TableBench, MMLU STEM | 21 | May 11, 2026 | ||
| General Multimodal Reasoning | NaturalBench | 21 | May 11, 2026 | ||
| General Multimodal Reasoning | LogicVista | 21 | May 11, 2026 | ||
| General Multimodal Reasoning | MMMU-Pro | 21 | May 11, 2026 | ||
| Multimodal Math Reasoning | MathVista | 21 | May 11, 2026 | ||
| Infrared Small Target Detection | NUAA-SIRST | 21 | May 11, 2026 | ||
| Infrared Small Target Detection | NUDT-SIRST | 21 | May 11, 2026 | ||
| Information Retrieval | BEIR-7 Average | 21 | May 11, 2026 | ||
| Information Retrieval | Quora | 21 | May 11, 2026 | ||
| Information Retrieval | ArguAna | 21 | May 11, 2026 |