Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2513 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fraud Detection | DigitalMusic | 15 | Feb 26, 2026 | ||
| Fraud Detection | InstantVideo | 15 | Feb 26, 2026 | ||
| Legal Question Answering | JEC-QA | 15 | Feb 26, 2026 | ||
| Mathematical Reasoning | Aggregate AIME24, AMC, MATH500, Minerva, Olympiad bench | 15 | Feb 26, 2026 | ||
| Sentence-Level Confidence Prediction | FEVER | 15 | May 13, 2026 | ||
| Mathematical Reasoning | Average Across all Benchmarks | 15 | Mar 19, 2026 | ||
| Mathematical Reasoning | MATH 500 | 15 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 15 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 15 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 15 | Feb 26, 2026 | ||
| Agentic Performance | ACEBench Agent | 15 | Feb 26, 2026 | ||
| Math Reasoning | Math Reasoning Long Q, Long A (test) | 15 | Feb 26, 2026 | ||
| Long-form QA | Long-form QA Short Q, Long A (test) | 15 | Feb 26, 2026 | ||
| Text Summarization | Text Summarization Long Q, Short A (test) | 15 | Feb 26, 2026 | ||
| Machine Translation | Machine Translation Short Q, Short A (test) | 15 | Feb 26, 2026 | ||
| Speech Recognition | MCV Unseen Accents 100H (test) | 15 | Feb 26, 2026 | ||
| Speech Recognition | MCV Seen Accents 100H (test) | 15 | Feb 26, 2026 | ||
| Reasoning | AGI Eval EN | 15 | Feb 27, 2026 | ||
| Long Context Question Answering | MultiFieldQA | 15 | Feb 26, 2026 | ||
| General Assistant Tasks | GAIA | 15 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE | 15 | Feb 26, 2026 | ||
| Multimodal Mathematical Reasoning | MathVista | 15 | Feb 26, 2026 | ||
| Prompt Safety Detection | WildGuardMix (train) | 15 | Feb 26, 2026 | ||
| Prompt Safety Detection | WildGuardMix (test) | 15 | Feb 26, 2026 | ||
| Visual Understanding | CV-Bench | 15 | May 12, 2026 |