Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1309 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Large Language Model Evaluation | MMLU, GSM8K, GPQA, HUMANEVAL, TRUTHFULQA, IFEVAL | 23 | Mar 4, 2026 | ||
| HDR Video Quality Assessment | Beyond8Bits (test) | 23 | Mar 4, 2026 | ||
| Video Quality Assessment | SFV+HDR (test) | 23 | Mar 4, 2026 | ||
| Video Quality Assessment | LIVE-HDR (test) | 23 | Mar 4, 2026 | ||
| Phase retrieval | FFHQ 256 x 256 | 23 | Jun 30, 2026 | ||
| Long-Horizon User-Centric Interaction | τ2-Bench | 23 | Mar 4, 2026 | ||
| Code-Centric Agent Interaction | ColBench | 23 | Mar 4, 2026 | ||
| User-Centric Agent Interaction | UserGym | 23 | Mar 4, 2026 | ||
| Continual Learning | ImageNetR 5S | 23 | May 12, 2026 | ||
| Image Reconstruction | MS-COCO 256x256 2017 (val) | 23 | Apr 29, 2026 | ||
| Document Question Answering | DUDE | 23 | Mar 4, 2026 | ||
| Multi-way preference ranking | EDITREWARD-BENCH | 23 | May 12, 2026 | ||
| Implicit Concept Erasure | Ring-A-Bell | 23 | May 29, 2026 | ||
| Short-text Clustering | Clinc150 (test) | 23 | Feb 27, 2026 | ||
| Symbolic Regression | LSR-Synth Material Science | 23 | Jun 4, 2026 | ||
| Symbolic Regression | LSR-Synth Physics | 23 | Jun 4, 2026 | ||
| Referring Remote Sensing Image Segmentation | RefSegRS (val) | 23 | May 26, 2026 | ||
| Scientific Chart Understanding | CharXiv 1.0 | 23 | Feb 27, 2026 | ||
| Spatiotemporal prediction | Human3.6M 256x256 | 23 | Feb 26, 2026 | ||
| Text-to-image generation | FLUX.1-schnell 1.0 (dev) | 23 | Feb 26, 2026 | ||
| Robotic Manipulation | D4RL Kitchen-Partial | 23 | Jun 1, 2026 | ||
| change detection | Avg across SYSU, LEVIR, GVLM, CLCD, OSCD | 23 | Feb 26, 2026 | ||
| Video Referring | VideoRefer-Bench-D | 23 | May 19, 2026 | ||
| Node Classification | Ogbn-proteins (test) | 23 | May 25, 2026 | ||
| Image Understanding | MMBench | 23 | Apr 7, 2026 |