Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 934 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Election auditing sample size simulation | Florida (FL) Simulation | 28 | May 19, 2026 | ||
| Reasoning | BBH | 28 | Jun 25, 2026 | ||
| Single-turn Reasoning | AIME, GPQA, MMLU-Pro, ToolBench Aggregate | 28 | May 19, 2026 | ||
| Tool-use Reasoning | ToolBench | 28 | May 19, 2026 | ||
| Science Question Answering | GPQA | 28 | May 19, 2026 | ||
| Mathematical Reasoning | AIME 25 | 28 | May 19, 2026 | ||
| Mathematical Reasoning | AIME24 | 28 | May 19, 2026 | ||
| Video Visual Question Answering | VSI-Bench | 28 | May 26, 2026 | ||
| Code Understanding | CodeMMLU | 28 | May 19, 2026 | ||
| Math Reasoning | MMLU-Pro | 28 | May 19, 2026 | ||
| Ranking Stability Analysis | SimpleQA and 4 Hallucination Benchmarks | 28 | May 19, 2026 | ||
| Video compression and encryption | Video input data | 28 | May 19, 2026 | ||
| Image Classification | STL-10 | 28 | May 19, 2026 | ||
| Operator Learning | PDEBench SWE | 28 | May 18, 2026 | ||
| Operator Learning | PDEBench DR | 28 | May 18, 2026 | ||
| Wafer Map Defect Classification | WM811K | 28 | May 18, 2026 | ||
| Image-to-Text Retrieval | MIRFlickr-25K (test) | 28 | May 18, 2026 | ||
| Dynamics downstream task | Iso | 28 | May 18, 2026 | ||
| Machine Unlearning | WMDP-cyber 1.0 (test) | 28 | May 15, 2026 | ||
| Machine Unlearning | WMDP-chem 1.0 (test) | 28 | May 15, 2026 | ||
| Machine Unlearning | WMDP-bio 1.0 (test) | 28 | May 15, 2026 | ||
| Sensitivity Analysis of Radiomic Features | RadioLung | 28 | May 15, 2026 | ||
| Sensitivity Analysis of Radiomic Features | LUNA | 28 | May 15, 2026 | ||
| Scenario Reduction | VC Large-scale 50 instances (test) | 28 | May 15, 2026 | ||
| Scenario Reduction | VC Medium-scale 50 instances (test) | 28 | May 15, 2026 |