Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 676 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-objective Recommendation | MovieLens | 35 | Apr 10, 2026 | ||
| Multi-objective Recommendation | MovieLens | 35 | Apr 10, 2026 | ||
| General Reasoning | ARC-C | 35 | May 28, 2026 | ||
| Question Answering | TriviaQA | 35 | Apr 10, 2026 | ||
| Question Answering | TriviaQA | 35 | Apr 10, 2026 | ||
| Multiple-choice Question Answering | MMLU Medical subjects | 35 | Apr 10, 2026 | ||
| Health | MMLU-Pro Health (FR) X (test) | 35 | Apr 10, 2026 | ||
| Health | MMLU-Pro Health (EN) X (test) | 35 | Apr 10, 2026 | ||
| Biomedical Evaluation | FR-MEDICAL 7 French-language tasks (test) | 35 | Apr 10, 2026 | ||
| Multitask Language Understanding | MMLU Professional Medecine FR (test) | 35 | Apr 10, 2026 | ||
| Multitask Language Understanding | MMLU Professional Medecine EN (test) | 35 | Apr 10, 2026 | ||
| Multitask Language Understanding | MMLU Medical Genetics FR (test) | 35 | Apr 10, 2026 | ||
| Multitask Language Understanding | MMLU Medical Genetics EN (test) | 35 | Apr 10, 2026 | ||
| Multiple-choice Question Answering | MMLU Medical Subjects (test) | 35 | Apr 10, 2026 | ||
| SQL Generation | EHR SQL closed-weight models | 35 | Apr 10, 2026 | ||
| Average Zero-shot Performance | Aggregate of 8 tasks zero-shot | 35 | Apr 9, 2026 | ||
| Question Answering | HotpotQA | 35 | Apr 8, 2026 | ||
| Question Answering | MMLU | 35 | Apr 8, 2026 | ||
| Question Answering | StrategyQA | 35 | Apr 8, 2026 | ||
| AI-generated image detection | Chameleon | 35 | May 26, 2026 | ||
| Language Understanding and Question Answering | Downstream NLP Suite MMLU, BoolQ, PIQA, WinoGrande, HellaSwag, ARC-e, ARC-c, OBQA | 35 | Apr 7, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 35 | Apr 21, 2026 | ||
| Speed-of-Sound reconstruction | Real phantom data | 35 | Apr 3, 2026 | ||
| Remote Sensing Referring Expression Comprehension (RSREC) | RISBench (test) | 35 | Jun 16, 2026 | ||
| Jailbreaking | JBB Behaviors | 35 | Apr 3, 2026 |