Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 487 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fine-grained Image Classification | Flowers | 43 | Jun 29, 2026 | ||
| Multi-modal Perception Evaluation | MME Perception | 43 | Jul 7, 2026 | ||
| Brain disorder classification | PPMI | 43 | Apr 21, 2026 | ||
| Membership Inference Attack | AG News (test) | 43 | Feb 26, 2026 | ||
| Membership Inference Attack | XSum (test) | 43 | Feb 26, 2026 | ||
| Membership Inference Attack | arXivReasoning Sequence-level | 43 | Feb 26, 2026 | ||
| Code Generation | MBPP 3-shot | 43 | Jun 23, 2026 | ||
| Code | HumanEval+ | 43 | May 26, 2026 | ||
| Code Generation | MBPP+ | 43 | Feb 26, 2026 | ||
| Scientific Reasoning | MMLU-STEM | 43 | Jun 17, 2026 | ||
| Mathematical Reasoning | Minerva | 43 | Mar 4, 2026 | ||
| Single-hop Question Answering | PopQA (test) | 43 | Jul 7, 2026 | ||
| Mathematical Reasoning | AMC23 | 43 | Feb 26, 2026 | ||
| Scientific Reasoning | HiPhO 2024–2025 1.0 | 43 | Feb 26, 2026 | ||
| Conditional Shapley value estimation | Diabetes M=10 | 43 | Feb 26, 2026 | ||
| Agentic Workflow Success | τ2-bench | 43 | Mar 4, 2026 | ||
| 3D Scene Reconstruction | Mip-NeRF360 | 43 | Jun 23, 2026 | ||
| Persuasion classification | Winning Arguments (test) | 43 | Feb 26, 2026 | ||
| Object Hallucination Evaluation | MSCOCO | 43 | May 15, 2026 | ||
| Long-context evaluation | RULER 64k | 43 | May 19, 2026 | ||
| Video Multimodal Understanding | Video MME | 43 | Apr 21, 2026 | ||
| 3D semantic occupancy prediction | SurroundOcc (val) | 43 | Jun 23, 2026 | ||
| Image-to-text retrieval | DOCCI (test) | 43 | Mar 27, 2026 | ||
| Knowledge Insertion | WikiData recent | 43 | Feb 26, 2026 | ||
| Action Recognition | PKU-MMD (XSub) | 43 | Mar 19, 2026 |