Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2427 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dynamic Light Field Reconstruction | MPEG-GSC views (test) | 15 | Apr 13, 2026 | ||
| General Reasoning | Aggregated Reasoning Tasks 10-Task Combination | 15 | Apr 13, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite AIME24, AIME25, AMC23, GSM8K, MATH500 | 15 | Apr 13, 2026 | ||
| Explanation | Yelp | 15 | Apr 13, 2026 | ||
| Explanation | AM-Movies | 15 | Apr 13, 2026 | ||
| Recommendation | AM-Movies | 15 | Apr 13, 2026 | ||
| Explanation | AM-Electronics | 15 | Apr 13, 2026 | ||
| Recommendation | AM Electronics | 15 | Apr 13, 2026 | ||
| LLM Routing | Cold-start | 15 | Apr 13, 2026 | ||
| Reasoning | GPQA D | 15 | Jun 2, 2026 | ||
| Pose Estimation | Pelvic Bone (PB) | 15 | Apr 13, 2026 | ||
| Pose Estimation | PD | 15 | Apr 13, 2026 | ||
| Pose Estimation | Stanford Bunny (SB) | 15 | Apr 13, 2026 | ||
| Aspect Sentiment Triplet Extraction | Res 2015 (test) | 15 | Apr 13, 2026 | ||
| Brain Tumor Segmentation | BraTS 2020 | 15 | Apr 13, 2026 | ||
| General-Purpose Utility | General-Purpose Utility Evaluation v1 (avg) | 15 | Apr 13, 2026 | ||
| Response Safety | JailBreakV-28K (avg) | 15 | Apr 13, 2026 | ||
| Response Safety | MM-SafetyBench (avg) | 15 | Apr 13, 2026 | ||
| Image-to-Text Retrieval | Flickr30k 1,000 images, 5,000 captions | 15 | Apr 13, 2026 | ||
| Top-k Recommendation | Yelp 2018 | 15 | Apr 13, 2026 | ||
| Top-k Recommendation | Amazon Beauty | 15 | Apr 13, 2026 | ||
| Top-k Recommendation | ML-1M | 15 | Apr 13, 2026 | ||
| Prompt-embedding Optimization | Parti Prompts (36) | 15 | Apr 14, 2026 | ||
| Hate Speech Detection | Bangla | 15 | Apr 13, 2026 | ||
| Toxicity Detection | Bangla | 15 | Apr 13, 2026 |