Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 627 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Physical Commonsense Reasoning | PIQA | 36 | Jun 18, 2026 | ||
| Multi-agent Scenario Generation | nuScenes | 36 | Jun 5, 2026 | ||
| 3D Path Planning | Turbulent Flow Simulation Environment (test) | 36 | Jun 5, 2026 | ||
| Knowledge-conflict Question Answering | TriviaQA CF-RAG | 36 | Jun 5, 2026 | ||
| Knowledge-conflict Question Answering | PopQA CF-RAG | 36 | Jun 5, 2026 | ||
| Knowledge-conflict Question Answering | NQ Swap | 36 | Jun 5, 2026 | ||
| Character Probing | ARCANE In-Scenario The Underdogs, East Lynne (low-popularity unvalidated) | 36 | Jun 5, 2026 | ||
| Character Roleplay | ARCANE validated slice 5 novels (Overall) | 36 | Jun 5, 2026 | ||
| Character Roleplay | ARCANE validated slice (5 novels) (Out-of-world) | 36 | Jun 5, 2026 | ||
| Character Roleplay | ARCANE validated slice (5 novels) (In-world) | 36 | Jun 5, 2026 | ||
| Character Roleplay | ARCANE validated slice (5 novels) (In-Scenario) | 36 | Jun 5, 2026 | ||
| SLAM | ICL-NUIM and Real-world Trajectories | 36 | Jun 5, 2026 | ||
| Question Answering | LongBench V1 | 36 | Jun 4, 2026 | ||
| Gradient Inversion Attack | MNIST (test) | 36 | Jun 4, 2026 | ||
| Novel View Synthesis | Glossy Blender | 36 | Jun 4, 2026 | ||
| Motion Estimation | MOT17, MOT20, SoccerNet, DanceTrack Combined (test) | 36 | Jun 4, 2026 | ||
| Flare Removal Quality Assessment | LL-Bench (test) | 36 | Jun 2, 2026 | ||
| Agent Safety Evaluation | ToolEmu | 36 | Jun 2, 2026 | ||
| Image Classification | ImageNet-C severity level 5, continual setting | 36 | Jun 2, 2026 | ||
| Image Classification | ImageNet-C Severity 5 Episodic (val) | 36 | Jun 2, 2026 | ||
| Deepfake Detection | DF40 Average | 36 | Jun 2, 2026 | ||
| Deepfake Detection | DF40 (FE) | 36 | Jun 2, 2026 | ||
| Deepfake Detection | DF40 (EFS) | 36 | Jun 2, 2026 | ||
| Instruction Following | IFEval | 36 | Jun 2, 2026 | ||
| Multi-turn Conversation | MT-Bench | 36 | Jun 2, 2026 |