Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1187 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Calibration and Measurement | 14 social science constructs (Sample Dataset) | 24 | May 13, 2026 | ||
| Reward Modeling | PPE-P latest (test) | 24 | May 13, 2026 | ||
| Reward Modeling | RewardBench latest (test) | 24 | May 13, 2026 | ||
| Page-level reranking | MMDocIR 1.0 (test) | 24 | May 13, 2026 | ||
| Traffic Prediction | Trentino SMS IN | 24 | May 13, 2026 | ||
| Language Modeling | Safe Prompts (test) | 24 | May 13, 2026 | ||
| Value Alignment | BeaverTails (test) | 24 | May 13, 2026 | ||
| Value Alignment | WildGuard (test) | 24 | May 13, 2026 | ||
| Tool Planning | ToolBench | 24 | May 13, 2026 | ||
| Tool Planning | UltraTool | 24 | May 13, 2026 | ||
| Tool Planning | Multimedia | 24 | May 13, 2026 | ||
| Tool Planning | HuggingFace | 24 | May 13, 2026 | ||
| Tool Sequence Prediction | Multimedia | 24 | May 13, 2026 | ||
| Tool Sequence Prediction | HuggingFace | 24 | May 13, 2026 | ||
| Evaluation | SIB200 (test) | 24 | May 13, 2026 | ||
| Multi-modal Large Language Model Evaluation | MME | 24 | May 13, 2026 | ||
| PDE Discovery | React-Diff PDE | 24 | May 13, 2026 | ||
| PDE Discovery | KdV–Burgers PDE | 24 | May 13, 2026 | ||
| PDE Discovery | KS PDE | 24 | May 13, 2026 | ||
| PDE Identification | Fisher-KPP PDE | 24 | May 13, 2026 | ||
| Mathematical Problem Solving | Olympiad | 24 | May 13, 2026 | ||
| Mathematical Problem Solving | MINERVA | 24 | May 13, 2026 | ||
| Mathematical Problem Solving | MATH 500 | 24 | May 13, 2026 | ||
| Mathematical Problem Solving | AIME 2025 | 24 | May 13, 2026 | ||
| Mathematical Problem Solving | AIME 2024 | 24 | May 13, 2026 |