Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 367 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fault Intensity Diagnosis | Cavitation Short | 51 | Apr 21, 2026 | ||
| Mathematical Reasoning | Gaokao2023 (test) | 51 | Apr 20, 2026 | ||
| Question Answering | CommonsenseQA | 51 | Apr 20, 2026 | ||
| Question Answering | MMLU | 51 | Apr 20, 2026 | ||
| Question Answering | MATH | 51 | Apr 20, 2026 | ||
| Question Answering | MGSM | 51 | Apr 20, 2026 | ||
| Question Answering | MedMCQA | 51 | Apr 20, 2026 | ||
| Question Answering | SciQ | 51 | Apr 20, 2026 | ||
| Coding | LiveCodeBench v6 | 51 | Jun 23, 2026 | ||
| Utility Judgment | TREC DL | 51 | Apr 14, 2026 | ||
| Utility Judgment | WebAP | 51 | Apr 14, 2026 | ||
| Reasoning | BBH | 51 | Jul 3, 2026 | ||
| Video Saliency Prediction | DHF1K | 51 | Apr 13, 2026 | ||
| Mathematical Reasoning | AIME24 | 51 | Jun 5, 2026 | ||
| Science Question Answering | SQA IMG | 51 | Jun 18, 2026 | ||
| Long-context Reasoning | BABILong 4k | 51 | Apr 8, 2026 | ||
| Object Hallucination Evaluation | POPE Random, Popular, Adversarial v1.0 | 51 | Apr 7, 2026 | ||
| Object Hallucination Evaluation | CHAIR MSCOCO v1.0 (val) | 51 | Apr 7, 2026 | ||
| Hallucination Evaluation | HaluEval | 51 | May 20, 2026 | ||
| Video Question Answering | MMVU | 51 | Mar 31, 2026 | ||
| Multi-image visual reasoning | BLINK | 51 | Jun 30, 2026 | ||
| Speech Recognition | LibriSpeech LS-Ave | 51 | Mar 26, 2026 | ||
| Robot Manipulation | MimicGen Square D2 | 51 | Jun 19, 2026 | ||
| Text-to-Image Generation | DiffusionDB (test) | 51 | Jun 11, 2026 | ||
| Code Generation | MBPP+ | 51 | Jun 4, 2026 |