Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2773 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Forecasting | Spatio-Temporal Synthetic Dataset 1.0 (test) | 14 | Feb 26, 2026 | ||
| Correlation Reasoning | Spatio-Temporal Synthetic Dataset 1.0 (test) | 14 | Feb 26, 2026 | ||
| Entity Reasoning | Spatio-Temporal Synthetic Dataset 1.0 (test) | 14 | Feb 26, 2026 | ||
| Etiological Reasoning | Spatio-Temporal Synthetic Dataset 1.0 (test) | 14 | Feb 26, 2026 | ||
| Tool-augmented reasoning | BFCL Multi-Turn v3 | 14 | Feb 26, 2026 | ||
| Text-to-Visualization | Text2Vis | 14 | Feb 26, 2026 | ||
| Science Question Answering | GPQA Main | 14 | Feb 26, 2026 | ||
| Massive Multitask Language Understanding | MMLU | 14 | Feb 26, 2026 | ||
| Dialogue Response Generation | KEEM (KMSC memories) 1.0 (test) | 14 | Feb 26, 2026 | ||
| Named Entity Recognition | PxCorpus | 14 | Feb 26, 2026 | ||
| Spoken Language Understanding | MEDIA | 14 | Feb 26, 2026 | ||
| Classification | AMEND_LLM | 14 | Feb 26, 2026 | ||
| Aspect Term Extraction | Restaurant 2014 (test) | 14 | Feb 26, 2026 | ||
| Binary Fact-checking | MeetingBank | 14 | Feb 26, 2026 | ||
| Binary Fact-checking | MediaSum | 14 | Feb 26, 2026 | ||
| Binary Fact-checking | REVEAL | 14 | Feb 26, 2026 | ||
| Binary Fact-checking | Claim Verify | 14 | Feb 26, 2026 | ||
| Multi-turn Conversation | MT-Bench | 14 | Feb 26, 2026 | ||
| Code Generation | HumanEval | 14 | Feb 26, 2026 | ||
| Long-context language modeling | InfiniteBench (test) | 14 | Apr 10, 2026 | ||
| Memory Management | Memalpha (val) | 14 | Jun 25, 2026 | ||
| Node Classification | Cora | 14 | Feb 26, 2026 | ||
| Node Classification | PubMed | 14 | Feb 26, 2026 | ||
| Node Classification | 14 | Feb 26, 2026 | |||
| Toxicity Evaluation | AttaQ | 14 | Feb 26, 2026 |