Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 874 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-modal Image Fusion | MRI-CT (test) | 30 | Feb 26, 2026 | ||
| Spatial Reasoning | VSTI-Bench | 30 | May 27, 2026 | ||
| Image Retrieval | ImageNet100 | 30 | Apr 7, 2026 | ||
| Industrial Anomaly Detection | MMAD | 30 | Feb 26, 2026 | ||
| Spatial Reasoning (Video) | VSI-Bench | 30 | May 27, 2026 | ||
| Multimodal Perception | HR-4K | 30 | Jun 30, 2026 | ||
| Jailbreak Detection | Zulu | 30 | Feb 26, 2026 | ||
| Jailbreak Detection | Base64 | 30 | Feb 26, 2026 | ||
| Jailbreak Detection | DrAttack | 30 | Feb 26, 2026 | ||
| Jailbreak Detection | PAIR | 30 | Feb 26, 2026 | ||
| Jailbreak Detection | AutoDAN | 30 | Feb 26, 2026 | ||
| Jailbreak Detection | GCG | 30 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Maze2D large v1 | 30 | May 26, 2026 | ||
| Offline Reinforcement Learning | Maze2D medium v1 | 30 | May 26, 2026 | ||
| Adversarial Attack Imperceptibility | GenImage | 30 | Feb 26, 2026 | ||
| Sentiment Analysis | SST-2 | 30 | Feb 26, 2026 | ||
| Data Encryption | Text files | 30 | Feb 26, 2026 | ||
| Rule-Inconsistency Task Classification | RIT (Rule-Inconsistency Tasks) | 30 | Feb 26, 2026 | ||
| Quantitative evaluation of LLM feedback against human gold standards | 50 SOC analysis reports (test) | 30 | Feb 26, 2026 | ||
| Explanation Hardening Evaluation | GTSRB 2.5% utility loss, ϵ = 9, δ = 10⁻⁵ (test) | 30 | Feb 26, 2026 | ||
| Explanation Hardening Evaluation | CIFAR-100 8% utility loss, ϵ = 10, δ = 10⁻⁵ (test) | 30 | Feb 26, 2026 | ||
| Explanation Hardening Evaluation | CIFAR-10 10% utility loss, ϵ = 8, δ = 10⁻⁵ (test) | 30 | Feb 26, 2026 | ||
| Multi-turn Jailbreaking | StrongReject (test) | 30 | Feb 26, 2026 | ||
| Transfer Attack | POPE | 30 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 | 30 | Feb 26, 2026 |