Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1609 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Helpfulness | AdvGLUE | 20 | Mar 4, 2026 | ||
| Helpfulness | SimpleQA | 20 | Mar 4, 2026 | ||
| Harmlessness | Stereotype | 20 | Mar 4, 2026 | ||
| Harmlessness | XsTest | 20 | Mar 4, 2026 | ||
| Software Engineering | SWE-Bench Multilingual 1.0 (test) | 20 | Mar 4, 2026 | ||
| Collaborative 3D Object Detection | OPV2V | 20 | Mar 4, 2026 | ||
| Safety Evaluation | BeaverTails Evaluation | 20 | Mar 4, 2026 | ||
| Mathematical Reasoning | GSM8K | 20 | Mar 4, 2026 | ||
| LVLM Evaluation | MMStar | 20 | May 1, 2026 | ||
| Motion Reasoning | ReMoT 16k (test) | 20 | Mar 4, 2026 | ||
| Multimodal Question Answering | MMQA k=1 | 20 | May 28, 2026 | ||
| Super-Resolution | Navier-Stokes (NS) 2x from PDEBench native grid (test) | 20 | Mar 4, 2026 | ||
| Multimodal Relation Reasoning | R-Bench | 20 | Mar 4, 2026 | ||
| Multimodal Relation Reasoning | MMRel | 20 | Mar 4, 2026 | ||
| Graph Classification | FINGERPRINT TU Dataset | 20 | Mar 4, 2026 | ||
| Graph Classification | LETTER-L TU Dataset | 20 | Mar 4, 2026 | ||
| Graph Classification | LETTER-M TU Dataset | 20 | Mar 4, 2026 | ||
| Graph Classification | LETTER-H TU Dataset | 20 | Mar 4, 2026 | ||
| Graph Classification | COX2 TU Dataset | 20 | Mar 4, 2026 | ||
| Compositional Image Generation | ComplexCompo 300 | 20 | Mar 4, 2026 | ||
| Articulated Shape Reconstruction | PartNet-Mobility v1 (test) | 20 | Mar 4, 2026 | ||
| Articulation Axis Estimation | PartNet-Mobility v1 (test) | 20 | Mar 4, 2026 | ||
| Joint-level Kinematic Estimation | PartNet-Mobility 3-part objects (test) | 20 | Mar 4, 2026 | ||
| Articulated Object Modeling | PartNet-Mobility 3 movable parts | 20 | Mar 4, 2026 | ||
| Image-based Retrieval | M5Product | 20 | Mar 4, 2026 |