Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1529 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Cross-domain graph property classification | ogbg-molbbbp -> ogbg-molbace (test) | 20 | Jun 30, 2026 | ||
| Question Answering | DocBench | 20 | Jun 30, 2026 | ||
| Information-gathering reasoning | Clue Selector Game (CSG) (evaluation set) | 20 | Jun 30, 2026 | ||
| Action Recognition | NTU 120 (X-view) | 20 | Jun 30, 2026 | ||
| Action Recognition | NTU-120 (X-sub) | 20 | Jun 30, 2026 | ||
| Tool-invocation hijacking to RCE | Agent Security Scenarios Old LLM Lineup | 20 | Jun 30, 2026 | ||
| Structured Pruning | CIFAR-10 (test) | 20 | Jun 30, 2026 | ||
| Image-to-text retrieval | IMDB | 20 | Jun 30, 2026 | ||
| Spatial Reasoning | SpatialEval Spatial-Map (20% train) | 20 | Jun 30, 2026 | ||
| Spatial Reasoning | SpatialEval Spatial-Grid (20% train) | 20 | Jun 30, 2026 | ||
| Spatial Reasoning | SpatialEval Maze-Nav 20% (train) | 20 | Jun 30, 2026 | ||
| Multi-Layer Spatial Relationship Accuracy | MD-3k Same subset | 20 | Jun 30, 2026 | ||
| Multi-Layer Spatial Relationship Accuracy | MD-3k Reverse subset | 20 | Jun 30, 2026 | ||
| multi-hop question answering | HOTPOT-QA | 20 | Jun 30, 2026 | ||
| science QA with short final answers | SCI-QA | 20 | Jun 30, 2026 | ||
| competition-style proof and derivation | AIME 21-24 | 20 | Jun 30, 2026 | ||
| broad-domain factual and professional reasoning | MMLU PRO | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | VQDiff (Generated) | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | Infinity (Generated) | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | VAR Generated | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | Taming (Generated) | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | RAR generated images | 20 | Jun 30, 2026 | ||
| Image Attribution Detection | LlamaGen generated images | 20 | Jun 30, 2026 | ||
| IBS Estimation | SEER stom. | 20 | Jun 30, 2026 | ||
| IBS Estimation | SEER liver | 20 | Jun 30, 2026 |