Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1792 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Stair Traversal | Simulated Stairs 12cm Height | 18 | Jun 24, 2026 | ||
| Mathematical Reasoning | AIME24 | 18 | Jun 24, 2026 | ||
| Chart-based Question Answering | ChartWalker Bench | 18 | Jun 24, 2026 | ||
| Lean type to informal description retrieval | mathlib (test) | 18 | Jun 24, 2026 | ||
| Visual Hallucination Evaluation | AMBER Discriminative | 18 | Jun 24, 2026 | ||
| Visual Hallucination Evaluation | AMBER Generative | 18 | Jun 24, 2026 | ||
| Data Copying Detection | Cross-architecture Setting GM/GN | 18 | Jun 24, 2026 | ||
| Part-aware explanation quality | PartImageNet OOD | 18 | Jun 24, 2026 | ||
| Language Modeling | Alpaca Cleaned (lower-level) | 18 | Jun 24, 2026 | ||
| Language Modeling | OpenOrca (upper-level) | 18 | Jun 24, 2026 | ||
| Rule Explanation Generation | Annotated Rule-Explanation Data Phase 3 | 18 | Jun 24, 2026 | ||
| Binary ill-posedness detection | SituatedQA | 18 | Jun 23, 2026 | ||
| Backdoor Attack | CIFAR-10 | 18 | Jun 23, 2026 | ||
| Code Generation | MBPP | 18 | Jun 23, 2026 | ||
| Code Generation | HumanEval | 18 | Jun 23, 2026 | ||
| Mathematical Reasoning | MATH 500 | 18 | Jun 23, 2026 | ||
| Spatio-temporal signal recovery | D4 | 18 | Jun 23, 2026 | ||
| Spatio-temporal signal recovery | D3 | 18 | Jun 23, 2026 | ||
| Spatio-temporal signal recovery | D2 | 18 | Jun 23, 2026 | ||
| Spatio-temporal signal recovery | D1 | 18 | Jun 23, 2026 | ||
| Training Iteration Efficiency | Qwen3-0.6B base (train) | 18 | Jun 23, 2026 | ||
| Action Selection | AdaptSim | 18 | Jun 23, 2026 | ||
| Knowledge Editing | Bi-ZsRE 1600 edits (test) | 18 | Jun 23, 2026 | ||
| Question Answering | TruthfulQA | 18 | Jun 23, 2026 | ||
| Open-ended Text Generation | WikiText | 18 | Jun 23, 2026 |