Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2369 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Conformal Prediction | Living-17 (test) | 15 | Jun 8, 2026 | ||
| Conformal Prediction | Living-17 | 15 | Jun 8, 2026 | ||
| Web Agent Task Completion | HLE | 15 | Jun 8, 2026 | ||
| Web Agent Task Completion | Browsecomp | 15 | Jun 8, 2026 | ||
| Tool-Calling Decision Making | When2Call (test) | 15 | Jun 8, 2026 | ||
| Spatial perception and reasoning | VSI-Bench (offline) | 15 | Jun 8, 2026 | ||
| Fine-grained Motion Video Understanding | FAVOR-Bench | 15 | Jun 8, 2026 | ||
| Model Steering | WaterBirds (test) | 15 | Jun 8, 2026 | ||
| Language Modeling | Text8 (val) | 15 | Jun 8, 2026 | ||
| Signal Reconstruction | EEG real 1D datasets (test) | 15 | Jun 8, 2026 | ||
| Signal Reconstruction | WSN real 1D datasets (test) | 15 | Jun 8, 2026 | ||
| Signal Reconstruction | ECG real 1D datasets (test) | 15 | Jun 8, 2026 | ||
| Regression | 4 Tabular Regression Datasets (Event user-attend, Beer beer-pos, Trial site-success, HM item-sales) | 15 | Jun 8, 2026 | ||
| General Language Understanding | 10-benchmark suite average | 15 | Jun 8, 2026 | ||
| Multi-Agent Coordination | TJ environment (test) | 15 | Jun 8, 2026 | ||
| Link Prediction | MovieLen-1M | 15 | Jun 5, 2026 | ||
| Link Prediction | Baby | 15 | Jun 5, 2026 | ||
| Link Prediction | MovieLen-1M | 15 | Jun 5, 2026 | ||
| Link Prediction | Baby | 15 | Jun 5, 2026 | ||
| Prefill Throughput | Synthetic | 15 | Jun 5, 2026 | ||
| Decode Throughput Generation | NVIDIA B200 GPU | 15 | Jun 5, 2026 | ||
| End-to-end Text Generation | NVIDIA B200 GPU Overall Generation | 15 | Jun 5, 2026 | ||
| Generative Modeling | ImageNet 256x256 (train) | 15 | Jun 5, 2026 | ||
| Safety-Utility Trade-off Evaluation | AgentHarm | 15 | Jun 5, 2026 | ||
| Long Video Reasoning | LongVideoBench | 15 | Jun 5, 2026 |