Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 398 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | BreakHis | 49 | Jun 30, 2026 | ||
| Image Classification | DomainNet-126 | 49 | Mar 5, 2026 | ||
| Multi-modal Reasoning | MMVet (test) | 49 | May 26, 2026 | ||
| Text Summarization | DialogueSUM (test) | 49 | Mar 18, 2026 | ||
| Over-refusal | Wildjailbreak (Benign) | 49 | Mar 17, 2026 | ||
| Retinal Anomaly Detection | OCTDL (test) | 49 | Feb 26, 2026 | ||
| Motion | nuScenes (val) | 49 | Apr 3, 2026 | ||
| Harmful Meme Detection | FHM | 49 | May 29, 2026 | ||
| Robotic Manipulation | RLBench (test) | 49 | Mar 20, 2026 | ||
| Object Hallucination Probing | GQA POPE Popular | 49 | Apr 10, 2026 | ||
| Super-Resolution | Urban100 | 49 | Jun 19, 2026 | ||
| MRI Super-Resolution | fastMRI Brain T2-weighted (test) | 48 | Jul 8, 2026 | ||
| Backdoor Poisoning Sample Isolation | CIFAR10 (train) | 48 | Jul 8, 2026 | ||
| Dataset Splitting for Backdoor Defense | GTSRB | 48 | Jul 8, 2026 | ||
| Gene Regulatory Network Inference | Simulated Gene Regulatory Network full sweep | 48 | Jul 7, 2026 | ||
| Speech Reconstruction | LibriTTS + ESC-50 clean-100 (test) | 48 | Jul 7, 2026 | ||
| State Estimation | Lorenz-96 arctan observation operator | 48 | Jul 2, 2026 | ||
| State Estimation | Lorenz-96 quadratic capped observation operator (test) | 48 | Jul 2, 2026 | ||
| LLM Prefill throughput | LLM Prompt Length 512 (pp512) | 48 | Jul 2, 2026 | ||
| LLM Prefill throughput | LLM Prompt Length 256 (pp256) | 48 | Jul 2, 2026 | ||
| LLM Prefill throughput | LLM Prompt Length 128 (pp128) | 48 | Jul 2, 2026 | ||
| Diffusion Adaptation | Elementfire | 48 | Jul 1, 2026 | ||
| Diffusion Adaptation | Hornify | 48 | Jul 1, 2026 | ||
| Diffusion Adaptation | Expedition | 48 | Jul 1, 2026 | ||
| Diffusion Adaptation | Cyberpunk | 48 | Jul 1, 2026 |