Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1551 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Token-level Uncertainty Quantification | MIMIC-DI | 20 | May 28, 2026 | ||
| Mathematical Reasoning | MATH500 | 20 | May 28, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 20 | May 28, 2026 | ||
| Reference-grounded News Verification | Wash. Post | 20 | May 28, 2026 | ||
| Reference-grounded News Verification | USA Today | 20 | May 28, 2026 | ||
| Reference-grounded News Verification | Guardian | 20 | May 28, 2026 | ||
| Reference-grounded News Verification | BBC | 20 | May 28, 2026 | ||
| Science Question Answering | SQA | 20 | Jul 1, 2026 | ||
| Question Answering | MMLU-Pro Computer Science | 20 | May 28, 2026 | ||
| Multiple-choice Question Answering | MMLU-Pro CS | 20 | May 28, 2026 | ||
| Professional Knowledge Reasoning | MMLU-Pro | 20 | May 28, 2026 | ||
| Event-to-Intensity Reconstruction | IEIMat Synthesized Data Static | 20 | May 28, 2026 | ||
| Physical Video Evaluation | Physics-IQ | 20 | Jun 4, 2026 | ||
| Semantic Segmentation | ZOD (val) | 20 | May 28, 2026 | ||
| General Reasoning | SQuAD | 20 | May 28, 2026 | ||
| General Reasoning | TriviaQA | 20 | May 28, 2026 | ||
| General Reasoning | NQ | 20 | May 28, 2026 | ||
| General Reasoning | LB-R | 20 | May 28, 2026 | ||
| Software Engineering | SWE-Bench Verified | 20 | May 28, 2026 | ||
| Multimodal Speech Understanding | MMSU All (test) | 20 | May 28, 2026 | ||
| Multimodal Speech Understanding | MMSU Paralinguistic subset (test) | 20 | May 28, 2026 | ||
| Preference Prediction | MovieLens 10k | 20 | May 28, 2026 | ||
| Few-shot Action Recognition | UCF101 5-way K-shot (test) | 20 | May 28, 2026 | ||
| Few-shot Action Recognition | HMDB51 5-way K-shot (test) | 20 | May 28, 2026 | ||
| Image Thresholding | Medical Images (test) | 20 | May 27, 2026 |