Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2510 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine Translation | Virām (test) | 15 | Feb 26, 2026 | ||
| Binary Question Answering | BoolQ | 15 | Feb 26, 2026 | ||
| Open-ended Question Answering | TruthfulQA | 15 | Feb 26, 2026 | ||
| Audio Understanding | MMSU (test) | 15 | Feb 26, 2026 | ||
| Text-to-Speech | InstructTTSEval EN | 15 | Feb 26, 2026 | ||
| Long Context Understanding | HELMET | 15 | Apr 6, 2026 | ||
| Long Context Understanding | MRCR | 15 | Mar 24, 2026 | ||
| Code Generation | MBPP | 15 | Feb 26, 2026 | ||
| Code Generation | CodeContests | 15 | Feb 26, 2026 | ||
| Quality Estimation | WMT en-de 22 | 15 | Feb 26, 2026 | ||
| Prompt Injection Attacks | OPEN-PROMPT-INJECTIONS | 15 | Feb 26, 2026 | ||
| Question Answering | SuperGPQA (test) | 15 | Feb 26, 2026 | ||
| Reasoning | MATH | 15 | May 12, 2026 | ||
| Document Contradiction Detection | ContraDoc (test) | 15 | Feb 26, 2026 | ||
| Web Browsing and Tool Use | BrowseComp+ original (test) | 15 | Feb 26, 2026 | ||
| General AI Assistant Tasks | GAIA Level 3 original (test) | 15 | Feb 26, 2026 | ||
| General AI Assistant Tasks | GAIA Level 2 original (test) | 15 | Feb 26, 2026 | ||
| General AI Assistant Tasks | GAIA Level 1 original (test) | 15 | Feb 26, 2026 | ||
| General AI Assistant Tasks | GAIA All levels original (test) | 15 | Feb 26, 2026 | ||
| Scientific Reasoning | SuperGPQA | 15 | Feb 27, 2026 | ||
| Long-form Factuality Verification | FactScore | 15 | Apr 14, 2026 | ||
| Instruction Following | MT-Bench en | 15 | Feb 26, 2026 | ||
| Visual Document Retrieval | JinaVDR | 15 | Feb 26, 2026 | ||
| Question Answering | GraphRAG-Benchmark MEDICAL | 15 | Feb 26, 2026 | ||
| Fine-grained Provenance Generation | PROVE-ASQA | 15 | Feb 27, 2026 |