Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2172 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Clustering | Glass (UCI) | 16 | Jun 4, 2026 | ||
| Clustering | Iris (UCI) | 16 | Jun 4, 2026 | ||
| Diffusion Fine-tuning | Mix-of-Show | 16 | May 12, 2026 | ||
| Scientific Knowledge | GPQA Diamond | 16 | May 12, 2026 | ||
| Scientific Knowledge | GPQA Diamond (out-of-distribution) | 16 | May 12, 2026 | ||
| Instruction Tuning | MT-Bench | 16 | Jun 4, 2026 | ||
| Citation Hallucination Detection | Citations PDF input mode rendered benchmark synthetic and real-world | 16 | May 12, 2026 | ||
| Code | MBPP | 16 | May 27, 2026 | ||
| Math | AIME25 | 16 | Jun 9, 2026 | ||
| Math | AIME24 | 16 | Jun 9, 2026 | ||
| Text-to-Image Generation | UniGenBench++ | 16 | May 12, 2026 | ||
| Text Summarization | CNN/DailyMail | 16 | May 12, 2026 | ||
| Story Generation | WritingPrompts | 16 | May 12, 2026 | ||
| Image Classification (Class Unlearning) | Fashion-MNIST | 16 | May 12, 2026 | ||
| Image Classification (Sample Unlearning) | Fashion-MNIST | 16 | May 12, 2026 | ||
| LLM Inference | LLaMA-7B v1 (serving) | 16 | May 12, 2026 | ||
| Instruction Injection Attack on Web Browser Agent | GitLab Short | 16 | May 12, 2026 | ||
| Instruction Injection Attack on Web Browser Agent | GitLab Medium | 16 | May 12, 2026 | ||
| Instruction Injection Attack on Web Browser Agent | GitLab Long | 16 | May 12, 2026 | ||
| Image Processing Inference | ViT (Vision Transformer) | 16 | May 12, 2026 | ||
| Video Reward Modeling | VideoRewardBench | 16 | May 11, 2026 | ||
| Multiple-choice question answering | ARC-E | 16 | May 15, 2026 | ||
| Intrusion Detection | OpTC 051 | 16 | May 11, 2026 | ||
| Mathematical Reasoning | HMMT 2024 | 16 | May 11, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 16 | May 11, 2026 |