Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2275 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Document Classification | MIMIC | 16 | Feb 26, 2026 | ||
| Document Classification | SCOTUS | 16 | Feb 26, 2026 | ||
| Document Classification | ECHR | 16 | Feb 26, 2026 | ||
| Reasoning | Reasoning domain benchmarks ARC-C, BBH, GPQA, CALM, KOR-BENCH | 16 | Feb 27, 2026 | ||
| Code Generation | Code domain benchmarks | 16 | Feb 27, 2026 | ||
| General Language Understanding and Reasoning | General domain benchmarks (test) | 16 | Feb 27, 2026 | ||
| Mathematical Reasoning | Math domain benchmarks (GSM8K, MATH500, Omni-Math, Olympiad, AIME'24) standard (test) | 16 | Feb 27, 2026 | ||
| Paragraph Segmentation | TEDPara (val) | 16 | Feb 26, 2026 | ||
| Deep Research | GAIA | 16 | Feb 26, 2026 | ||
| Hallucination detection | FAVA Annotated Dataset | 16 | Feb 26, 2026 | ||
| Rumor Victim Susceptibility | CoPHEME | 16 | Feb 26, 2026 | ||
| Fact-checking | FeLMWk | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM-Infinite Hard | 16 | Feb 26, 2026 | ||
| Aspect-conditioned Similarity | ASPECTSIM Span Level 1.0 (test) | 16 | Feb 26, 2026 | ||
| Value identification | ValuePrism | 16 | Feb 27, 2026 | ||
| Value identification | GLOBE | 16 | Feb 27, 2026 | ||
| Value identification | PVQ-RR | 16 | Feb 27, 2026 | ||
| Value identification | WVS | 16 | Feb 27, 2026 | ||
| Graduate-level Question Answering | GPQA Diamond (test) | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH (test) | 16 | Feb 26, 2026 | ||
| General QA Verification | PopQA | 16 | Feb 26, 2026 | ||
| General QA Verification | TriviaQA | 16 | Feb 26, 2026 | ||
| General QA Verification | NQ | 16 | Feb 26, 2026 | ||
| Multi-Hop QA Verification | 2wiki | 16 | Feb 26, 2026 | ||
| Multi-Hop QA Verification | Musique | 16 | Feb 26, 2026 |