Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1177 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Object Reconstruction | Multi-view Radar and Camera Dataset 1.0 (test) | 24 | May 29, 2026 | ||
| Automatic Speech Recognition | SPRING-INX Tamil | 24 | May 28, 2026 | ||
| Math Reasoning | AIME 2025 | 24 | May 28, 2026 | ||
| Math Reasoning | AIME 2024 | 24 | May 28, 2026 | ||
| Math Reasoning | Minerva | 24 | May 28, 2026 | ||
| Math Reasoning | MATH 500 | 24 | May 28, 2026 | ||
| Out-of-domain transfer | HumanEval, LiveCodeBench, and ReClor average (test) | 24 | May 28, 2026 | ||
| Mathematical Reasoning | AIME25 | 24 | May 28, 2026 | ||
| Mathematical Reasoning | Math Reasoning Overall | 24 | May 28, 2026 | ||
| Commonsense Reasoning | StrategyQA | 24 | Jun 1, 2026 | ||
| Overreach Evaluation | OVEREAGER | 24 | May 28, 2026 | ||
| Triplet Alignment | IntentEmo | 24 | May 28, 2026 | ||
| Semantic Textual Similarity | Big Patent (BP) | 24 | May 28, 2026 | ||
| Semantic Textual Similarity | MultiHate (MH) | 24 | May 28, 2026 | ||
| Semantic Textual Similarity | PaperCode (PC) | 24 | May 28, 2026 | ||
| Question Answering | LoCoMo (test) | 24 | May 28, 2026 | ||
| Scientific Reasoning | SciKnowEval Physics | 24 | May 28, 2026 | ||
| Scientific Reasoning | SciKnowEval Material | 24 | May 28, 2026 | ||
| Scientific Reasoning | SciKnowEval Biology | 24 | May 28, 2026 | ||
| Object Hallucination Evaluation | Object HalBench (test) | 24 | May 28, 2026 | ||
| Membership Inference Attack | MSC | 24 | May 28, 2026 | ||
| Membership Inference Attack | LoCoMo | 24 | May 28, 2026 | ||
| Membership Inference Attack | PerLTQA | 24 | May 28, 2026 | ||
| Next-move prediction | M2R | 24 | May 28, 2026 | ||
| Next-move prediction | M1-S | 24 | May 28, 2026 |