Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1693 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question-Answering | Llama Questions | 19 | Jul 9, 2026 | ||
| Dialogue Planning | P4G (test) | 19 | Jun 15, 2026 | ||
| Verifiable Judging | VerifyBench Hard | 19 | Jun 12, 2026 | ||
| Verifiable Judging | VerifyBench (full) | 19 | Jun 12, 2026 | ||
| Visual Question Answering | SeedBench | 19 | Jun 11, 2026 | ||
| 3D Object Detection | VoD | 19 | Jun 11, 2026 | ||
| Disease Diagnosis | ADNI MCI | 19 | Jun 17, 2026 | ||
| Job Shop Scheduling | Demirkol JSP instances | 19 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | MPE Predator Prey (Expert) | 19 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | MPE Predator Prey Medium | 19 | Jun 11, 2026 | ||
| Cycle-based Classification | Respiratory Sound Dataset Asthma vs COPD | 19 | Jun 11, 2026 | ||
| Subject-based Classification | Respiratory Sound Dataset Asthma vs COPD | 19 | Jun 11, 2026 | ||
| Change Detection | CLCD | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | WildRF (post-proc) | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | Loki (post-proc) | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | Chameleon post-proc | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | WildRF (original) | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | Loki (original) | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | Chameleon (original) | 19 | Jun 11, 2026 | ||
| AI-Generated Image Detection | SD Original | 19 | Jun 11, 2026 | ||
| Automatic Speech Recognition | OpenASR leaderboard (test) | 19 | Jul 7, 2026 | ||
| Error Recognition | WHO&WHEN Algorithm-Generated | 19 | Jun 11, 2026 | ||
| Error Recognition | WHO&WHEN Human-Crafted | 19 | Jun 11, 2026 | ||
| One-step-ahead forecasting | 2,217 real series | 19 | Jun 9, 2026 | ||
| Automatic Speech Recognition | LibriSpeech | 19 | Jun 11, 2026 |