Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1489 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hallucination Detection | Dolly Llama2-13B (test) | 21 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth Llama2-13B (test) | 21 | Feb 26, 2026 | ||
| Hallucination Detection | Dolly Llama2-7B (test) | 21 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth Llama2-7B (test) | 21 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K subset of 100 questions (test) | 21 | Apr 7, 2026 | ||
| Viewpoint classification | Immigration-3K | 21 | Feb 26, 2026 | ||
| Code Retrieval | MTEB Code | 21 | May 14, 2026 | ||
| Language Modeling | General Capability | 21 | Feb 26, 2026 | ||
| Safety Evaluation | HH-RLHF (test) | 21 | Feb 26, 2026 | ||
| Chinese Spelling Check | LEMON, CSCD-NS, and CS Combined | 21 | Feb 26, 2026 | ||
| Chinese Spelling Check | CS | 21 | Feb 26, 2026 | ||
| Chinese Spelling Check | LEMON | 21 | Feb 26, 2026 | ||
| Document Classification | EURLEX | 21 | May 19, 2026 | ||
| Language Understanding | INCLUDE base 44 | 21 | Feb 26, 2026 | ||
| Automatic Speech Recognition | MLC-SLM (dev) | 21 | Jun 11, 2026 | ||
| Knowledge Tracing | EdNet-500 (test) | 21 | Feb 26, 2026 | ||
| Knowledge Tracing | DBE-KT22 (test) | 21 | Feb 26, 2026 | ||
| Fairness | DermoBench Fairness | 21 | Feb 26, 2026 | ||
| Reasoning | DermoBench Reasoning | 21 | Feb 26, 2026 | ||
| Diagnosis | DermoBench Out-of-Distribution | 21 | Feb 26, 2026 | ||
| Diagnosis | DermoBench In-Distribution | 21 | Feb 26, 2026 | ||
| Morphology | DermoBench Morphology | 21 | Feb 26, 2026 | ||
| Code Agent | SWE-Bench Verified | 21 | Jul 2, 2026 | ||
| Script confusion mitigation | FLEURS zh-trad (test) | 21 | Feb 26, 2026 | ||
| Script confusion mitigation | FLEURS zh-sim (test) | 21 | Feb 26, 2026 |