Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2197 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Movement time prediction | LUIDA | 16 | Apr 7, 2026 | ||
| Movement time prediction | Clark 2020 | 16 | Apr 7, 2026 | ||
| Image Classification | Fashion-MNIST | 16 | May 21, 2026 | ||
| 3D shape assembly | Breaking Bad (Everyday) | 16 | Apr 7, 2026 | ||
| Retrieval | MisstepMath | 16 | Apr 7, 2026 | ||
| Text-to-Image Generation | COCO 10K | 16 | Apr 7, 2026 | ||
| Document Clustering | 20 Newsgroups | 16 | Jun 2, 2026 | ||
| Pose Estimation | M2UD | 16 | Apr 7, 2026 | ||
| General Reasoning Evaluation | Average (AVG) | 16 | Apr 7, 2026 | ||
| Complex Reasoning | BBH | 16 | Apr 7, 2026 | ||
| Scientific Reasoning | GPQA | 16 | Apr 7, 2026 | ||
| Multitask Language Understanding | MMLU | 16 | Apr 7, 2026 | ||
| Behavioral Cloning | Obstacle | 16 | Apr 7, 2026 | ||
| Behavioral Cloning | Planar Quadrotor | 16 | Apr 7, 2026 | ||
| Behavioral Cloning | P2P Small | 16 | Apr 7, 2026 | ||
| Behavioral Cloning | P2P-Cost | 16 | Apr 7, 2026 | ||
| Temporal Coherence Verification | Fluid Video 1.0 (test) | 16 | Apr 7, 2026 | ||
| Next Frame Selection | Fluid Video 1.0 (test) | 16 | Apr 7, 2026 | ||
| Multi-Agent System Performance | Database | 16 | Apr 7, 2026 | ||
| Multi-Agent System Performance | Research | 16 | Apr 7, 2026 | ||
| Multi-Agent System Performance | Coding | 16 | Apr 7, 2026 | ||
| Semantic Alignment Evaluation | Expert-labeled feature relevance dataset | 16 | Apr 7, 2026 | ||
| Mathematical Reasoning | AIME | 16 | Apr 7, 2026 | ||
| Complex query answering | Warden Alert Inductive, 33% qualifier coverage | 16 | Apr 6, 2026 | ||
| Knowledge Graph Completion | Warden Alert Transductive | 16 | Apr 6, 2026 |