Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 523 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Reasoning | HRBench-4K | 41 | Jun 30, 2026 | ||
| Object Detection | COCO | 41 | May 19, 2026 | ||
| Classification | 11 natural domain benchmarks average (test) | 41 | Apr 23, 2026 | ||
| CTR Prediction | TaobaoAds | 41 | May 29, 2026 | ||
| Mathematical Reasoning | Math | 41 | Apr 27, 2026 | ||
| 3D scene editing | Curated evaluation scenes from IN2N, Mip-NeRF 360, BlendedMVS, and LLFF novel viewpoints | 41 | Apr 23, 2026 | ||
| Cross-view Geo-localization | SUES-200 Satellite→Drone (200m) | 41 | May 12, 2026 | ||
| Reward Modeling | RewardBench (full) | 41 | May 19, 2026 | ||
| Semantic Verifier Evaluation | SceneCritic | 41 | Apr 15, 2026 | ||
| Long-horizon agentic task | HLE | 41 | May 26, 2026 | ||
| Personalized Image Aesthetic Assessment | LAPIS | 41 | Apr 21, 2026 | ||
| OOD Detection | FGVCAircraft | 41 | Jun 5, 2026 | ||
| Language Generation | WikiText-103 | 41 | May 27, 2026 | ||
| Linear regression | Linear regression with Toeplitz Sigma_a r=0.5 | 41 | Apr 14, 2026 | ||
| Out-of-Distribution Detection | OBQA to MMLU | 41 | Apr 13, 2026 | ||
| Out-of-Distribution Detection | RACE to MMLU | 41 | Apr 13, 2026 | ||
| Mathematical Reasoning | Olympiad | 41 | Jun 2, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 41 | May 15, 2026 | ||
| Image Classification | Digits | 41 | Jun 4, 2026 | ||
| Medical Report Generation | IU X-Ray (test) | 41 | Apr 21, 2026 | ||
| Robot Manipulation | LIBERO Average | 41 | Jun 9, 2026 | ||
| NSFW suppression | P4D | 41 | Jun 30, 2026 | ||
| Multistep Soft Reasoning | MuSR | 41 | Apr 23, 2026 | ||
| Option Pricing | S&P 500 index options 317 longer prediction horizons | 41 | Apr 2, 2026 | ||
| Knowledge-based Visual Question Answering | OK-VQA | 41 | Jul 2, 2026 |