Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1886 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Link Prediction | WikiArt-MKG v1 | 18 | Mar 4, 2026 | ||
| Link Prediction | WN9-IMG | 18 | Mar 4, 2026 | ||
| Retrosynthesis | USPTO-50k With Reaction Type | 18 | Mar 4, 2026 | ||
| Fine-grained Detection | MMFakeBench 10000 (test) | 18 | Mar 4, 2026 | ||
| Fine-grained Detection | MMFakeBench 1000 (val) | 18 | Mar 4, 2026 | ||
| Anomaly Detection | Bitcoin-OTC | 18 | May 27, 2026 | ||
| Tool-Use Agent Evaluation | BFCL Multiturn (OOD) v3 (test) | 18 | Mar 4, 2026 | ||
| LLM Alignment | UltraFeedback (test) | 18 | Mar 4, 2026 | ||
| Speech Quality Assessment | Kids | 18 | Mar 4, 2026 | ||
| Speech Quality Assessment | Wild | 18 | Mar 4, 2026 | ||
| Speech Quality Assessment | Noisy | 18 | Mar 4, 2026 | ||
| Speech Quality Assessment | Clean | 18 | Mar 4, 2026 | ||
| Safety Alignment | HEx-PHI | 18 | May 20, 2026 | ||
| Text-to-image | MJHQ 30K (test) | 18 | Mar 4, 2026 | ||
| Text-to-image | COCO 30K (test) | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium-Expert) | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium-Replay) | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah JointNoise Shift (Medium) | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah BodyMass Shift (Medium) | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium-Expert BodyMass Shift | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium-Replay JointNoise Shift | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Walker2D Medium-Replay BodyMass Shift | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah Medium-Expert 1T10S | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium-Expert 1T10S | 18 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium-Replay 1T10S | 18 | Mar 4, 2026 |