Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 437 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CelebA-HQ | 46 | Feb 26, 2026 | ||
| Gaussian Deblurring | FFHQ | 46 | May 21, 2026 | ||
| AIGI Detection | SynthWildx | 46 | May 22, 2026 | ||
| AIGI Detection | AIGCDetect | 46 | May 22, 2026 | ||
| Visual Question Answering | LLaVA Evaluation Suite GQA, MMB, MMMU, MME, VQAv2, VQAtext, POPE, SQA, SEED, MMVet 1.5 7B (various) | 46 | Feb 26, 2026 | ||
| Camera Pose Estimation | RealEstate10K | 46 | May 19, 2026 | ||
| Medical Image Segmentation | LA (10% labels) | 46 | Jul 3, 2026 | ||
| Hallucination Detection | TyDiQA-GP | 46 | Jun 2, 2026 | ||
| Safety Classification | XSTest | 46 | Jul 8, 2026 | ||
| Automatic Speech Recognition | AMI | 46 | Jun 17, 2026 | ||
| Machine Translation | Flores-200 Romance group xx->en (test) | 46 | Feb 26, 2026 | ||
| Machine Translation | Flores-200 Romance group en->xx (test) | 46 | Feb 26, 2026 | ||
| Toxicity Mitigation | RealToxicityPrompts challenging | 46 | Feb 26, 2026 | ||
| Author Response Generation | Author Response Generation (ARG) dataset | 46 | Feb 26, 2026 | ||
| Reasoning | MATH | 46 | Apr 23, 2026 | ||
| Reasoning | OBQA | 46 | May 28, 2026 | ||
| Question Answering | SearchQA | 46 | Jun 2, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Aggregate | 46 | Jun 30, 2026 | ||
| Dialogue | MT-Bench (test) | 46 | Feb 26, 2026 | ||
| Jailbreak Attack | PAIR | 46 | Jul 7, 2026 | ||
| Energy consumption estimation | LLM Energy Consumption (test) | 46 | Feb 27, 2026 | ||
| Mathematical Reasoning | AMC 23 | 46 | Feb 26, 2026 | ||
| Node Classification | Pokec-n | 46 | Jun 4, 2026 | ||
| Error Detection | Flowers102 | 46 | Apr 28, 2026 | ||
| Correlation with human evaluation | SEEDA E Base | 46 | Feb 26, 2026 |