Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2414 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-hop Reasoning | FanOutQA | 15 | Apr 29, 2026 | ||
| Multi-hop Reasoning | CRAG | 15 | Apr 29, 2026 | ||
| Multi-hop Reasoning | MuSiQue | 15 | Apr 29, 2026 | ||
| Multi-user Dialogue Response Generation | PAT | 15 | Apr 29, 2026 | ||
| Logical Reasoning | BBH | 15 | Apr 29, 2026 | ||
| General Knowledge Reasoning | MMLU-Pro | 15 | Apr 29, 2026 | ||
| Mathematical Reasoning | GSM8K | 15 | Apr 29, 2026 | ||
| Needle-in-the-Haystack retrieval | PG-19 mini 100K context | 15 | Apr 29, 2026 | ||
| Needle-in-the-Haystack retrieval | PG-19 mini 32K context | 15 | Apr 29, 2026 | ||
| Pixel-centric Understanding | V* | 15 | Apr 28, 2026 | ||
| Multimodal Understanding | MMVet | 15 | Apr 28, 2026 | ||
| Long-Context Retrieval | RULER 8K | 15 | Jul 7, 2026 | ||
| Long-Context Retrieval | RULER 32K | 15 | Jun 12, 2026 | ||
| Speech Enhancement | VB-DMD | 15 | Apr 28, 2026 | ||
| Mathematical Problem Solving | MATH 500 | 15 | Apr 28, 2026 | ||
| Combinatorial Optimization | MIS | 15 | May 1, 2026 | ||
| Intention recognition | IntentQA (test) | 15 | Apr 28, 2026 | ||
| PII Extraction | Private data (test) | 15 | Apr 28, 2026 | ||
| STEM Reasoning | MMLU STEM | 15 | May 21, 2026 | ||
| Affordance reasoning | ReasonAff | 15 | May 4, 2026 | ||
| Rationale-based retrieval | ESConv (test) | 15 | Apr 28, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 15 | Apr 28, 2026 | ||
| Medical Image Segmentation | FUMPE | 15 | Apr 28, 2026 | ||
| Medical Image Segmentation | Scar | 15 | Apr 28, 2026 | ||
| Radar-Inertial Odometry | ardea 5 | 15 | Apr 28, 2026 |