Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1109 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Treatment Classification | Longitudinal Wearable Sensor Waveforms | 25 | May 12, 2026 | ||
| Joint Point Cloud Compression | Owlii | 25 | May 12, 2026 | ||
| Joint Point Cloud Compression | 8iVFB | 25 | May 12, 2026 | ||
| Point Forecasting | ETTh2 | 25 | Jul 3, 2026 | ||
| Multi-task Language Understanding | MMLU-Pro | 25 | May 11, 2026 | ||
| Science Question Answering | ARC Challenging | 25 | May 11, 2026 | ||
| Unconditional image generation | MNIST Binary | 25 | May 11, 2026 | ||
| Novel View Synthesis | Ev-DeblurBlender synthetic (test) | 25 | May 11, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 25 | May 11, 2026 | ||
| Class-Incremental Learning | Tiny-ImageNet 20 tasks | 25 | May 18, 2026 | ||
| Laboratory Science Knowledge Evaluation | LAB-Bench 2 821 (Evaluation) | 25 | May 8, 2026 | ||
| High-Level Expert Knowledge Evaluation | HLE Gold 149 | 25 | May 8, 2026 | ||
| Biomedical Intelligence Evaluation | BixBench 205 (Evaluation) | 25 | May 8, 2026 | ||
| Offline Reinforcement Learning | OGBench cube-triple (ct) | 25 | May 12, 2026 | ||
| Knowledge Tracing | Algebra 05 | 25 | May 12, 2026 | ||
| Concept Steering | AxBench (Held-in) | 25 | May 8, 2026 | ||
| Time Series Anomaly Detection | KPI | 25 | May 29, 2026 | ||
| Zero-shot Text-to-Speech | Seed-TTS en (test) | 25 | Jun 2, 2026 | ||
| Multimodal Search | MMSearch | 25 | May 7, 2026 | ||
| Language Modeling | OpenWebText2 | 25 | May 22, 2026 | ||
| Math | iGSM | 25 | May 7, 2026 | ||
| Medical | MedCalc | 25 | May 7, 2026 | ||
| Hyperspectral Anomaly Detection | Urban I | 25 | Jun 5, 2026 | ||
| Hyperspectral Anomaly Detection | Airport II | 25 | Jun 5, 2026 | ||
| Logical Reasoning | RP LP Domain, Npred ≤ 60, 6 < δ ≤ 12 | 25 | May 7, 2026 |