Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2159 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD Detection | In: CIFAR-100, Out: TinyImageNet (test) | 16 | May 26, 2026 | ||
| Multi-Agent Reinforcement Learning (Predator-Prey) | MPE PP_9/3 | 16 | May 21, 2026 | ||
| Multi-Agent Reinforcement Learning (Predator-Prey) | MPE PP_6/2 | 16 | May 21, 2026 | ||
| Multi-Agent Reinforcement Learning (Predator-Prey) | MPE PP_3/1 | 16 | May 21, 2026 | ||
| Medical Task | Medical | 16 | May 21, 2026 | ||
| Embodied Task | Embodied | 16 | May 21, 2026 | ||
| Agent Task | Agent | 16 | May 21, 2026 | ||
| Coding Reasoning | HumanEval | 16 | Jun 16, 2026 | ||
| No-Reference Video Quality Assessment | YT-SFV SDR_ANIMAL_5NGJ.MP4 (sample) | 16 | May 20, 2026 | ||
| Voice Steganalysis | Voice Steganalysis QIM, PMS, LSB, AHCM | 16 | May 20, 2026 | ||
| Document Parsing | OmniDocBench EN | 16 | May 20, 2026 | ||
| Aesthetic scoring | PPAINT | 16 | May 20, 2026 | ||
| Classification | WIC | 16 | May 20, 2026 | ||
| Molecule Retrieval | MassSpecGym Formula Split | 16 | Jun 30, 2026 | ||
| Image Space Diffusion | CelebA 64x64 | 16 | May 20, 2026 | ||
| Open-loop planning | Waymo | 16 | May 20, 2026 | ||
| Open-loop planning | NAVSIM | 16 | May 20, 2026 | ||
| Neural speech coding | LibriSpeech clean (test) | 16 | Jun 8, 2026 | ||
| Mathematical Problem Solving | AIME 2026 | 16 | Jul 2, 2026 | ||
| Language Modeling | Tulu3 tydiqa (Evaluation) | 16 | May 20, 2026 | ||
| Chat | Alpaca | 16 | May 20, 2026 | ||
| Code Generation | MBPP | 16 | May 20, 2026 | ||
| Code Generation | HumanEval | 16 | May 20, 2026 | ||
| Mathematics | MATH 500 | 16 | May 20, 2026 | ||
| Mathematics | GSM8K | 16 | May 20, 2026 |