Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 769 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reasoning and Language Modeling | Reasoning Suite (ARC, HellaSwag, PIQA, WinoGrande, MMLU, OpenBookQA, Real-world QA) Zero-shot Llama-3.1-8B-Instruct with Alpaca calibration | 32 | Mar 19, 2026 | ||
| Language Modeling | Llama-2 13B | 32 | Apr 13, 2026 | ||
| Paper Quality Evaluation | ICLR 2025 (test) | 32 | May 27, 2026 | ||
| Linear Regression | Concrete 40% MNAR | 32 | Mar 19, 2026 | ||
| Linear Regression | Concrete 20% MNAR | 32 | Mar 19, 2026 | ||
| Linear Regression | Gas 40% MNAR | 32 | Mar 19, 2026 | ||
| Machine Unlearning | TOFU Forget05 Phi-1.5B model (5%) | 32 | May 22, 2026 | ||
| Visual Question Answering | GQA | 32 | Jun 16, 2026 | ||
| Regression | PFN REG | 32 | Jun 4, 2026 | ||
| Regression | Tabarena REG | 32 | Jun 4, 2026 | ||
| Truthfulness | TruthfulQA | 32 | May 12, 2026 | ||
| Automatic Speech Recognition | ASRU 2019 (test) | 32 | Apr 13, 2026 | ||
| New View Synthesis | LLFF (R) | 32 | Mar 17, 2026 | ||
| Text-to-Image Generation | sDCI | 32 | May 19, 2026 | ||
| Mathematical Reasoning | Math Benchmarks | 32 | Mar 17, 2026 | ||
| Truthfulness | TruthfulQA | 32 | Mar 17, 2026 | ||
| Adversarial Attack | Kaggle | 32 | Mar 17, 2026 | ||
| Adversarial Attack | Kaggle Credit Card Fraud | 32 | Mar 17, 2026 | ||
| Web Information Extraction | SWDE expanded (test) | 32 | Mar 17, 2026 | ||
| Web Information Extraction | SWDE original (test) | 32 | Mar 17, 2026 | ||
| Zero-shot Commonsense Reasoning | Commonsense Reasoning Suite | 32 | Mar 17, 2026 | ||
| Prompt Injection Attack | InjecAgent | 32 | Mar 16, 2026 | ||
| Online overhead computation | WAN4 | 32 | Mar 16, 2026 | ||
| Online overhead computation | WAN3 | 32 | Mar 16, 2026 | ||
| Online overhead computation | WAN2 | 32 | Mar 16, 2026 |