Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 154 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Logical Reasoning | ZebraLogic (test) | 90 | May 29, 2026 | ||
| Terminal task completion | Terminal-bench 2.0 | 90 | Jun 23, 2026 | ||
| Code Generation | MBPP | 90 | Feb 26, 2026 | ||
| Multi-Hop Knowledge Graph Question Answering | WebQSP | 90 | Jul 8, 2026 | ||
| Camera pose estimation | TUM dynamics | 90 | May 8, 2026 | ||
| Inference Efficiency | HumanEval | 90 | May 13, 2026 | ||
| Open Vocabulary Semantic Segmentation | COCO Stuff without background | 90 | May 13, 2026 | ||
| Tabular Data Synthesis Fidelity | steel | 90 | Feb 26, 2026 | ||
| Tabular Data Synthesis Fidelity | biodeg | 90 | Feb 26, 2026 | ||
| Commonsense reasoning | MMLU | 90 | Jul 7, 2026 | ||
| Adversarial Attack Success Rate | AdvBench | 90 | Jun 16, 2026 | ||
| Semantic Segmentation | PASCAL Context 59 | 90 | Jun 9, 2026 | ||
| Paraphrase Detection | MRPC | 90 | Jun 15, 2026 | ||
| Image Classification | Resisc45 (test) | 90 | Jun 9, 2026 | ||
| Object Detection | NDDA stop sign images (test) | 90 | Feb 26, 2026 | ||
| Base-to-New Generalization | Caltech101 | 90 | Jul 2, 2026 | ||
| Novel View Synthesis | Mip-NeRF360 (test) | 90 | Jun 9, 2026 | ||
| Multimodal Abstractive Summarization | MM-Sum mid-high-resource (test) | 90 | Feb 27, 2026 | ||
| Question Answering | OBQA (test) | 90 | Jun 30, 2026 | ||
| Text-based Person Search | CUHK-PEDES | 90 | May 15, 2026 | ||
| Locomotion | D4RL walker2d-medium-expert | 90 | May 19, 2026 | ||
| Generalized Few-Shot Object Detection | PASCAL VOC (Set 3) | 90 | Feb 26, 2026 | ||
| Generalized Few-Shot Object Detection | PASCAL VOC (Set 2) | 90 | Feb 26, 2026 | ||
| Text Generation | LM1B (test) | 90 | Jun 11, 2026 | ||
| OOD Detection | iNaturalist (OOD) / ImageNet-1k (ID) 1.0 (test) | 90 | Apr 28, 2026 |