Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2039 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reinforcement Learning | MuJoCo Hopper v5 | 17 | Mar 4, 2026 | ||
| Reinforcement Learning | MuJoCo Ant v5 | 17 | Mar 4, 2026 | ||
| Reinforcement Learning | MuJoCo HalfCheetah v5 | 17 | Mar 4, 2026 | ||
| CNS tumor classification | PBT | 17 | May 26, 2026 | ||
| Information Retrieval | BrowseComp-Plus | 17 | Mar 4, 2026 | ||
| Opinion Alignment | ANES | 17 | Mar 4, 2026 | ||
| Opinion Alignment | WoM | 17 | Mar 4, 2026 | ||
| Opinion Alignment | smartvote | 17 | Mar 4, 2026 | ||
| Opinion Alignment | American National Election Studies (ANES) 2020 Time Series (test) | 17 | Mar 4, 2026 | ||
| Opinion Alignment | Wahl-O-Mat (WoM) March 2025 (test) | 17 | Mar 4, 2026 | ||
| Opinion Alignment | smartvote 2023 Swiss national elections (test) | 17 | Mar 4, 2026 | ||
| Chime-in Timing | MUIR (test) | 17 | Mar 4, 2026 | ||
| Chime-in Reason | MUIR (test) | 17 | Mar 4, 2026 | ||
| Web Browsing and Comparison | Browsecomp VL | 17 | Mar 4, 2026 | ||
| Information Seeking Question Answering | InfoSeek | 17 | Mar 4, 2026 | ||
| PDE Solving | KdV | 17 | May 13, 2026 | ||
| Hate Speech Analysis | HatefulMemes | 17 | Mar 4, 2026 | ||
| Probe rotation estimation | Ten standard ultrasound planes | 17 | Mar 4, 2026 | ||
| Probe translation dimension estimation | Echocardiography ten standard planes | 17 | Mar 4, 2026 | ||
| Medical Visual Question Answering | VQA-Med (test) | 17 | Mar 10, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 | 17 | Mar 4, 2026 | ||
| Protein sequence design | CATH 4.3 (150-300 residues) | 17 | Mar 4, 2026 | ||
| Protein sequence design | CATH 0-150 residues 4.3 | 17 | Mar 4, 2026 | ||
| HDR | FFHQ 256 x 256 | 17 | Jun 30, 2026 | ||
| Novel View Synthesis | ScanNet 8 views | 17 | Mar 25, 2026 |