Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2134 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mixture separation | gated-pool DLBCL | 16 | Jun 9, 2026 | ||
| Mixing matrix estimation | Wine Semi-synthetic | 16 | Jun 9, 2026 | ||
| Mixing matrix estimation | Digits Semi-synthetic | 16 | Jun 9, 2026 | ||
| Bayesian Optimal Experimental Design | Structured Cascade | 16 | Jun 9, 2026 | ||
| Sycophancy Detection | Social Sycophancy (Held-out) | 16 | Jun 8, 2026 | ||
| Multi-view Reasoning | BLINK | 16 | Jun 8, 2026 | ||
| Pneumonia Classification | PneumoniaMNIST v1 (test) | 16 | Jun 8, 2026 | ||
| Jailbreak Detection | AdvBench Vicuna-7B | 16 | Jun 8, 2026 | ||
| Jailbreak Detection | AdvBench Mistral-7B | 16 | Jun 8, 2026 | ||
| Jailbreak Detection | AdvBench Llama3-8B | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Mixing Attack | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Perturbation Attack | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Paraphrase Attack | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Prompt Attack | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Direct Attack | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Llama-2 | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL PaLM-2 | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL Claude | 16 | Jun 8, 2026 | ||
| Machine-generated Text Detection | DetectRL GPT-3.5 | 16 | Jun 8, 2026 | ||
| Noisy-label detection | CIFAR-10 | 16 | Jun 8, 2026 | ||
| Zero-shot Voice Cloning | Seed-TTS-Eval zh (test) | 16 | Jun 8, 2026 | ||
| Zero-shot Voice Cloning | Seed-TTS-Eval en (test) | 16 | Jun 8, 2026 | ||
| Video Temporal Grounding | SVHighlights (test) | 16 | Jun 8, 2026 | ||
| Automatic Speech Recognition | ERJ 1.0 (non-native) | 16 | Jun 8, 2026 | ||
| Agent task execution | SkillsBench 11 domains | 16 | Jun 8, 2026 |