Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2688 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Retrosynthesis | HCMO-retro Multi-constraint | 14 | Apr 8, 2026 | ||
| Retrosynthesis | HCMO-retro All Constrained Tasks | 14 | Apr 8, 2026 | ||
| Sequential Recommendation | Movielens 1M | 14 | Apr 8, 2026 | ||
| Sequential Recommendation | Netflix | 14 | Apr 8, 2026 | ||
| Sequential Recommendation | Microlens | 14 | Apr 8, 2026 | ||
| Image Dehazing | Neuron Dataset | 14 | Apr 8, 2026 | ||
| Microscopy Image Restoration | Organoids 2 | 14 | Apr 8, 2026 | ||
| Image Dehazing | Organoids1 (test) | 14 | Apr 8, 2026 | ||
| Medical Question Answering | MMLU | 14 | Apr 8, 2026 | ||
| Report Generation | Heartcare-Bench I (test) | 14 | Apr 8, 2026 | ||
| Report Generation | Heartcare-Bench S (test) | 14 | Apr 8, 2026 | ||
| Closed-QA | Heartcare-BenchI | 14 | Apr 8, 2026 | ||
| Closed-QA | Heartcare-BenchS | 14 | Apr 8, 2026 | ||
| Compositional Image Generation | Positional CLEVR 1 Component | 14 | Apr 8, 2026 | ||
| Compositional Image Generation | Relational CLEVR 1 Component | 14 | Apr 8, 2026 | ||
| Compositional Image Generation | FFHQ 1 Component | 14 | Apr 8, 2026 | ||
| Multi-hop Reasoning | MuSiQue | 14 | Apr 8, 2026 | ||
| Multi-hop Reasoning | HotpotQA | 14 | Apr 8, 2026 | ||
| Long-context Reasoning | LongBench | 14 | Apr 8, 2026 | ||
| General Reasoning | MMLU-CF | 14 | Apr 8, 2026 | ||
| General Reasoning | BBH | 14 | Apr 8, 2026 | ||
| Mathematical Reasoning | GSM8K | 14 | Apr 8, 2026 | ||
| Mathematical Reasoning | OlympiadBench Math | 14 | Apr 8, 2026 | ||
| Mathematical Reasoning | MATH | 14 | Apr 8, 2026 | ||
| General Reasoning Average | Aggregate OBQA, CSQA, SIQA, ARC, MMLU, GSM8K-MC, AQUA | 14 | Apr 8, 2026 |