Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2171 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Prompt Quality Evaluation | 500 randomly sampled prompts | 16 | May 12, 2026 | ||
| Demographics Classification | Longitudinal Wearable Sensor Waveforms | 16 | May 12, 2026 | ||
| Automated Program Repair | QuixBugs-Java 40 bugs | 16 | May 12, 2026 | ||
| Automated Program Repair | HumanEval Java (164 tasks) | 16 | May 12, 2026 | ||
| Automated Program Repair | Defects4J 835 bugs v2.0 | 16 | May 12, 2026 | ||
| Automated Program Repair | SWE-bench Verified 500 instances | 16 | May 12, 2026 | ||
| Classification | eucalyptus | 16 | May 12, 2026 | ||
| Ground Segmentation | KITTI-360 | 16 | May 12, 2026 | ||
| Ground Segmentation | nuScenes | 16 | May 12, 2026 | ||
| Ground Segmentation | SemanticKITTI | 16 | May 12, 2026 | ||
| Action Quality Assessment | Rhythmic Gymnastics (test) | 16 | May 12, 2026 | ||
| Lane Centerline Perception and Reasoning | OpenLane-V2 subset A 6 | 16 | May 12, 2026 | ||
| Multimodal Tool-Use | MMSearch-Plus | 16 | May 12, 2026 | ||
| Multimodal Tool-Use | TIR-Bench | 16 | May 12, 2026 | ||
| Engineering Design Optimization | three_bar_truss | 16 | Jun 26, 2026 | ||
| Legal Reasoning | CaseHold | 16 | May 12, 2026 | ||
| Dialogue Generation | Vicuna | 16 | May 12, 2026 | ||
| Dialogue Generation | SelfInst | 16 | May 12, 2026 | ||
| Dialogue Generation | UnNI | 16 | May 12, 2026 | ||
| Dialogue Generation | S-NI | 16 | May 12, 2026 | ||
| Dialogue Generation | DollyEval | 16 | May 12, 2026 | ||
| Root Cause Analysis | Petshop temporal traffic scenario | 16 | May 12, 2026 | ||
| Root Cause Analysis | Petshop high traffic scenario | 16 | May 12, 2026 | ||
| Root Cause Analysis | Petshop low traffic scenario | 16 | May 12, 2026 | ||
| Clustering | Ecoli (UCI) | 16 | Jun 4, 2026 |