Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1599 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Evaluation | MSSbench (test) | 20 | Mar 17, 2026 | ||
| Safety Evaluation | SIUO (test) | 20 | Mar 17, 2026 | ||
| Safety Evaluation | MM-SafetyBench (test) | 20 | May 19, 2026 | ||
| Safety Evaluation | SPA-VL (test) | 20 | Mar 17, 2026 | ||
| Safety Evaluation | Beavertails-V (test) | 20 | Mar 17, 2026 | ||
| Anomaly Detection | Bitcoin-Alpha | 20 | Jun 4, 2026 | ||
| Contextual forecasting | Context Is Key | 20 | Mar 17, 2026 | ||
| Novel View Synthesis | LLFF 4 input views (test) | 20 | Mar 17, 2026 | ||
| Image Fusion | AWMM-100K Rain condition | 20 | Jun 26, 2026 | ||
| Multimodal Reasoning Evaluation | CRYSTAL | 20 | Mar 16, 2026 | ||
| Problem-solving | GSM8K | 20 | Mar 19, 2026 | ||
| Action Recognition | SAR-RARP50 | 20 | Mar 16, 2026 | ||
| Hallucination Detection | Hallucination Bench image | 20 | Jul 7, 2026 | ||
| Synthetic Data Utility | CIC-IDS 2017 | 20 | Mar 16, 2026 | ||
| Referring Expression Grounding | D^3 Intra-scenario | 20 | Mar 16, 2026 | ||
| Preference Alignment | UF-P-4 | 20 | Mar 16, 2026 | ||
| Preference Alignment | UF-P 2 | 20 | Mar 16, 2026 | ||
| Natural Language Understanding and Reasoning | MMLU, ARC-c, HellaSwag, BOOLQ, PIQA, WinoGrande zero-shot | 20 | Mar 16, 2026 | ||
| Desnowing | AIO-IR Desnowing | 20 | Jun 23, 2026 | ||
| Deblurring | AIO-IR Deblurring | 20 | Jun 23, 2026 | ||
| Video Generation | nuScenes | 20 | Jul 1, 2026 | ||
| Goal-reaching | PushT 50 Samples (test) | 20 | Mar 13, 2026 | ||
| Goal-reaching | PointMaze UMaze (test) | 20 | Mar 13, 2026 | ||
| Goal-reaching | Wall 50 samples (test) | 20 | Mar 13, 2026 | ||
| Training Data Extraction | EchoTrace | 20 | Mar 13, 2026 |