Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1945 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reading Comprehension | Race-H | 18 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 | 18 | Feb 26, 2026 | ||
| Table Fact Verification | TabFact small | 18 | Feb 26, 2026 | ||
| Referring Expression Grounding | Ferret-Bench | 18 | Feb 26, 2026 | ||
| Referring Expression Grounding | LVIS-Ref | 18 | Feb 26, 2026 | ||
| Situated 3D Question Answering | SQA3D | 18 | Mar 31, 2026 | ||
| Monocular Depth Estimation | NYU v2 (val) | 18 | Jun 24, 2026 | ||
| CXR-to-report generation | OpenI (test) | 18 | Feb 26, 2026 | ||
| Multiple Choice Video-QA | Perception (test) | 18 | Feb 26, 2026 | ||
| Super-Resolution | Urban100 | 18 | May 19, 2026 | ||
| Super-Resolution | B100 | 18 | May 19, 2026 | ||
| Super-Resolution | Set5 | 18 | May 19, 2026 | ||
| Action Recognition | EK100, SSV2, and K400 | 18 | Feb 26, 2026 | ||
| Zero-shot Classification | Classification Datasets (MMLU, OBQA, ARC-e, WinoGrande, ARC-c, PIQA, HellaSwag) | 18 | Feb 26, 2026 | ||
| Anomaly Detection | MVTec-AD Unified setting | 18 | Mar 25, 2026 | ||
| General Language Understanding | C-Eval (val) | 18 | Feb 26, 2026 | ||
| Action Recognition | Assembly101 | 18 | Feb 26, 2026 | ||
| Audio Deepfake Detection | MLAAD-EN | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH 18 (test) | 18 | Feb 26, 2026 | ||
| Novel View Synthesis | Neu3D (test) | 18 | Feb 26, 2026 | ||
| Natural Language Inference | XNLI Sw (test) | 18 | Feb 26, 2026 | ||
| Natural Language Inference | XNLI Sw (dev) | 18 | Feb 26, 2026 | ||
| Natural Language Inference | XNLI Hi (test) | 18 | Feb 26, 2026 | ||
| Sentiment Analysis | HinProd (test) | 18 | Feb 26, 2026 | ||
| Sentiment Analysis | HinProd (dev) | 18 | Feb 26, 2026 |