Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 402 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Target Response Induction | VLGuard | 48 | May 19, 2026 | ||
| Multimodal Evaluation Summary | Aggregated non-MME | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | WIND | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | TEMP | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | PM2.5 | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | ZAFNOO | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | CZELAN | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | AQWAN | 48 | May 19, 2026 | ||
| Long-term Time Series Forecasting | AQSHUNYI | 48 | May 19, 2026 | ||
| Instruction Tuning | TyDiQA, MMLU, BBH | 48 | May 18, 2026 | ||
| Temporal Grounding | Charades | 48 | May 15, 2026 | ||
| Temporal Grounding | ANet-RTL | 48 | May 15, 2026 | ||
| Short-term Time Series Forecasting | SP500 | 48 | May 15, 2026 | ||
| Short-term Time Series Forecasting | Website | 48 | May 15, 2026 | ||
| Short-term Time Series Forecasting | CarSales | 48 | May 15, 2026 | ||
| Agentic Task Performance | τ2-Bench Airline 1.0 (test) | 48 | May 13, 2026 | ||
| Agentic Task Performance | τ2-Bench Retail 1.0 (test) | 48 | May 13, 2026 | ||
| Heteroscedastic Regression | Synthetic | 48 | May 13, 2026 | ||
| Integral estimation | Spiral | 48 | May 13, 2026 | ||
| Integral estimation | 2D Dynamics modeling Spiral integral (test) | 48 | May 13, 2026 | ||
| Instance Segmentation | COCO | 48 | May 13, 2026 | ||
| Object Detection | COCO | 48 | May 13, 2026 | ||
| Red-teaming | Violence prompts | 48 | May 13, 2026 | ||
| Red-teaming | I2P Nudity prompts | 48 | May 13, 2026 | ||
| Confidence Estimation | VLCB Pooled Aggregate (test) | 48 | May 12, 2026 |