Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2013 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Driving Reasoning | Drive-Internal (test) | 17 | Apr 21, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 17 | Apr 21, 2026 | ||
| Multi-hop Question Answering | 2WikiMultiHop | 17 | Apr 21, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 17 | Apr 21, 2026 | ||
| Multi-player game search | Quadrothello | 17 | Apr 21, 2026 | ||
| Multi-player game search | Separed Teamhex | 17 | Apr 21, 2026 | ||
| Multi-player game search | Hey, That’s My Fish! | 17 | Apr 21, 2026 | ||
| Multi-player game search | Blokus | 17 | Apr 21, 2026 | ||
| Multi-player game search | Quadamazons | 17 | Apr 21, 2026 | ||
| Domain Generalization | VLCS | 17 | Apr 21, 2026 | ||
| Image Classification | TerraIncognita leave-one-domain-out (LODO) | 17 | Apr 21, 2026 | ||
| Domain Generalization | OfficeHome | 17 | Apr 21, 2026 | ||
| Mathematical Problem Solving | FlowVerse Text Plus DI+RP+EI+OQ | 17 | Apr 21, 2026 | ||
| Penalty Direction Prediction | Penalty Direction Prediction Two-class | 17 | Apr 21, 2026 | ||
| Penalty Direction Prediction | Penalty Direction Prediction 3-class | 17 | Apr 21, 2026 | ||
| Text-to-Video Generation | VBench T2V 15 | 17 | Apr 21, 2026 | ||
| Explanation Generation | CFMS | 17 | Apr 21, 2026 | ||
| Target Recognition | CFMS | 17 | Apr 21, 2026 | ||
| Identification | CFMS | 17 | Apr 21, 2026 | ||
| Video Editing | V2VBench | 17 | Apr 21, 2026 | ||
| Optical Character Recognition | IAM HW, EN | 17 | Apr 20, 2026 | ||
| Language Modeling | OpenWebText GPT-2 (val) | 17 | May 22, 2026 | ||
| Combinatorial Auction Efficiency | SRVM (Satellite Remote Value Model) | 17 | Apr 20, 2026 | ||
| Combinatorial Auction Efficiency | LSVM (Local Spectrum Value Model) | 17 | Apr 20, 2026 | ||
| Mathematical Reasoning | Minerva-Math | 17 | Jun 23, 2026 |