Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2279 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Discriminative Reasoning | RPEval Multi-MACRO, Explicit Memory | 16 | Feb 26, 2026 | ||
| Discriminative Reasoning | RPEval Single, Explicit Memory | 16 | Feb 26, 2026 | ||
| Generative task evaluation | Generative tasks single-preference setting | 16 | Feb 26, 2026 | ||
| Discriminative Task | RPEval Implicit Memory, Multi-Preference | 16 | Feb 26, 2026 | ||
| Discriminative Task | RPEval Implicit Memory, Single-Preference | 16 | Feb 26, 2026 | ||
| Generative tasks | Generative tasks multi-preference setting | 16 | Feb 26, 2026 | ||
| Multi-word Expression Identification | CoAM (test) | 16 | Feb 26, 2026 | ||
| Question Answering | Humanity's Last Exam | 16 | Feb 26, 2026 | ||
| Reasoning | NumS (test) | 16 | Feb 26, 2026 | ||
| Reasoning | ObjC (test) | 16 | Feb 26, 2026 | ||
| Reasoning | MOAS (test) | 16 | Feb 26, 2026 | ||
| Reasoning | CLF (test) | 16 | Feb 26, 2026 | ||
| Reasoning | LLC (test) | 16 | Feb 26, 2026 | ||
| Reasoning | MDM (test) | 16 | Feb 26, 2026 | ||
| Reasoning | Parity-NL (test) | 16 | Feb 26, 2026 | ||
| Programming Reasoning | LiveCodeBench v5 | 16 | Apr 2, 2026 | ||
| Short-term planning | AndroidControl Low | 16 | Feb 26, 2026 | ||
| Short-term planning | OmniAct Desktop | 16 | Feb 26, 2026 | ||
| Short-term planning | OmniAct-Web | 16 | Feb 26, 2026 | ||
| Short-term planning | GUI-Act-Web | 16 | Feb 26, 2026 | ||
| Speech-to-Text Question-Answering | OBQA | 16 | Apr 9, 2026 | ||
| Autoformalization | miniF2F (test) | 16 | Apr 8, 2026 | ||
| Formal Language Generation | SMILES-Bench | 16 | Feb 26, 2026 | ||
| Formal Language Generation | CPP-Bench | 16 | Feb 26, 2026 | ||
| Formal Language Generation | JSON-Bench | 16 | Feb 26, 2026 |