Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1434 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Survival | Synthetic | 21 | Jun 4, 2026 | ||
| Ranking | Synthetic | 21 | Jun 4, 2026 | ||
| Classification | Synthetic | 21 | Jun 4, 2026 | ||
| Regression | Synthetic | 21 | Jun 4, 2026 | ||
| General video understanding | PerceptionTest (PercTest) | 21 | Jun 2, 2026 | ||
| General video understanding | NExT-QA | 21 | Jun 2, 2026 | ||
| Long-video understanding | LongVideoBench (LVB) | 21 | Jun 2, 2026 | ||
| State Estimation | Pendulum | 21 | Jun 2, 2026 | ||
| Text-to-image generation | GenEval | 21 | Jun 11, 2026 | ||
| Visual Web Agent Navigation | DeepShop | 21 | Jun 2, 2026 | ||
| Circuit Localization | MCQA | 21 | Jun 2, 2026 | ||
| Time Series Forecasting | Fev-bench (test) | 21 | Jun 2, 2026 | ||
| Model Inversion Defense | Facescrub 224x224 (test) | 21 | Jun 2, 2026 | ||
| Text-to-Image Generation | UniGenBench 600 prompts (test) | 21 | Jun 2, 2026 | ||
| Regression | Protein | 21 | Jun 2, 2026 | ||
| Regression | Metro | 21 | Jun 2, 2026 | ||
| Regression | HEPC | 21 | Jun 2, 2026 | ||
| Regression | Abalone | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse yo 1.0 | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse 1.0 (si) | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse 1.0 (km) | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse 1.0 (my) | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse am 1.0 | 21 | Jun 2, 2026 | ||
| Safety Refusal Evaluation | PolyRefuse 1.0 (sw) | 21 | Jun 2, 2026 | ||
| Logical Reasoning | KK All | 21 | Jun 2, 2026 |