Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2361 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-agent debate | Mixed regime | 15 | Jun 18, 2026 | ||
| Multi-agent debate | Social regime | 15 | Jun 18, 2026 | ||
| Multi-agent debate | Closed regime | 15 | Jun 18, 2026 | ||
| Multi-agent debate | AlphaNLI | 15 | Jun 18, 2026 | ||
| Mathematical Problem Solving | MATH-500 simple-numeric-answer (Level 5) | 15 | Jun 18, 2026 | ||
| Binary Classification | IBD Cohort MRF-Likelihood ground truth | 15 | Jun 18, 2026 | ||
| Top-5 Ranking | Clinical IBD Likelihood Targets Mode 2 (10-patient pilot) | 15 | Jun 18, 2026 | ||
| Hybrid MI-SSVEP Classification | OpenBMI | 15 | Jun 18, 2026 | ||
| Steady-State Visual Evoked Potential Classification | OpenBMI | 15 | Jun 18, 2026 | ||
| Pair Matching | Two Moon (test) | 15 | Jun 18, 2026 | ||
| Subset Matching | two moon datasets (test) | 15 | Jun 18, 2026 | ||
| Workflow Generation | DRFLOW (original) | 15 | Jun 17, 2026 | ||
| Countdown | Countdown 3 | 15 | Jun 17, 2026 | ||
| Classification Attribution | ImageNet correctly classified samples (val) | 15 | Jun 17, 2026 | ||
| Reasoning | Average Multi-domain | 15 | Jun 17, 2026 | ||
| Graduate-level Science QA | GPQA D | 15 | Jun 17, 2026 | ||
| Mathematical Reasoning | AIME 25 | 15 | Jun 17, 2026 | ||
| Mathematical Reasoning | AIME 24 | 15 | Jun 17, 2026 | ||
| Image Deblurring | GoPro PGD attack, 20 iterations | 15 | Jun 17, 2026 | ||
| Image Deblurring | GoPro PGD attack, 5 iterations | 15 | Jun 17, 2026 | ||
| Image Deblurring | GoPro CosPGD attack 20 iterations | 15 | Jun 17, 2026 | ||
| Image Deblurring | GoPro CosPGD attack, 5 iterations | 15 | Jun 17, 2026 | ||
| fMRI prediction | HCP Movie (External) | 15 | Jun 17, 2026 | ||
| Land Use Land Cover Classification | CloudLULC-Set | 15 | Jun 17, 2026 | ||
| SFF estimation | NAKO (test) | 15 | Jun 17, 2026 |