Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2173 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME 2024 | 16 | May 11, 2026 | ||
| Text-to-SQL | PolySQL (test) | 16 | May 11, 2026 | ||
| Long Context Understanding | Ruler | 16 | May 11, 2026 | ||
| Language Understanding | ITALIC | 16 | May 11, 2026 | ||
| Language Understanding | MMLU-Redux Generative | 16 | May 11, 2026 | ||
| Language Understanding | MMLU CoT | 16 | May 11, 2026 | ||
| Meta-Evaluation | Aggregated Benchmarks (AIME, ARC, GSM8K, HE, MMLU, IT, RU, BFCL) | 16 | May 11, 2026 | ||
| Function Calling | BFCL | 16 | May 11, 2026 | ||
| Long-context Evaluation | Ruler | 16 | May 11, 2026 | ||
| Italian Language Understanding | ITALIC | 16 | May 11, 2026 | ||
| Language Understanding | MMLU | 16 | May 11, 2026 | ||
| Code Generation | HumanEval | 16 | May 11, 2026 | ||
| Mathematical Reasoning | GSM8K | 16 | May 11, 2026 | ||
| Question Answering | ARC | 16 | May 11, 2026 | ||
| Mathematical Reasoning | AIME | 16 | May 11, 2026 | ||
| Natural Language Understanding | italic cot custom | 16 | May 11, 2026 | ||
| Natural Language Understanding | italic fast | 16 | May 11, 2026 | ||
| Natural Language Understanding | ITALIC original | 16 | May 11, 2026 | ||
| Functional Code Generation | HumanEval 8 instruct cot (test) | 16 | May 11, 2026 | ||
| Mathematical Reasoning | AIME competition-level 2024 | 16 | May 11, 2026 | ||
| Reasoning | ARC Challenge Italian | 16 | May 11, 2026 | ||
| Reasoning | ARC Challenge | 16 | May 11, 2026 | ||
| Long-context Retrieval | RULER 32k context (test) | 16 | May 11, 2026 | ||
| Long-context Retrieval | RULER 4k context (test) | 16 | May 11, 2026 | ||
| Mathematical Reasoning | MATH 500 | 16 | May 11, 2026 |