Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1298 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Retrieval | MRMR | 23 | Jun 12, 2026 | ||
| Wireless transmitter placement | RadioMapSeer Deployment | 23 | Apr 27, 2026 | ||
| Spectral Compressive Imaging reconstruction | 10 simulated scenes | 23 | Apr 24, 2026 | ||
| In-context retrieval | In-context retrieval (lm-evaluation-harness) zero-shot | 23 | Apr 24, 2026 | ||
| Class-Incremental Learning | Seq-Cifar-100 | 23 | Apr 23, 2026 | ||
| Class-Incremental Learning | CIFAR-100 Seq | 23 | Apr 23, 2026 | ||
| Image Classification | EuroSAT | 23 | Jun 30, 2026 | ||
| Safety Verification | Oscillator 2D system | 23 | Apr 23, 2026 | ||
| Vulnerability detection and confirmation | VulcaN | 23 | Apr 23, 2026 | ||
| Vulnerability detection and confirmation | SecBench.js | 23 | Apr 23, 2026 | ||
| General AI assistant tasks | GAIA n=165 (dev) | 23 | Apr 23, 2026 | ||
| Speech Deepfake Detection | ICF | 23 | Apr 23, 2026 | ||
| LLM Judgment | TriviaQA | 23 | Apr 23, 2026 | ||
| LLM Judgment | HotpotQA | 23 | Apr 23, 2026 | ||
| LLM Judgment | Natural Questions (NQ) | 23 | Apr 23, 2026 | ||
| LLM Judgment | Auto-J | 23 | Apr 23, 2026 | ||
| LLM Judgment | UltraFeedback | 23 | Apr 23, 2026 | ||
| Safety Classification | OpenAI-moderation (test) | 23 | May 26, 2026 | ||
| Egocentric Human Activity Recognition | MMEA | 23 | Apr 23, 2026 | ||
| Node Classification | Arxiv | 23 | May 13, 2026 | ||
| Robotic Manipulation | SIMPLER | 23 | May 26, 2026 | ||
| Uncertainty Estimation | TriviaQA, SVAMP, and NQ Average | 23 | Apr 21, 2026 | ||
| Sparse-view CT Reconstruction | Sparse-view CT volumes 20-view | 23 | Apr 27, 2026 | ||
| Vectorized Map Construction | nuScenes | 23 | Apr 21, 2026 | ||
| Cultural Reasoning | CulturalBench | 23 | Apr 21, 2026 |