Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1159 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | Out-of-domain GSM-Hard, MultiArith, SVAMP | 24 | Jul 1, 2026 | ||
| Image Classification | Flower102 | 24 | Jul 1, 2026 | ||
| Long-context language modeling | LongBench | 24 | Jul 1, 2026 | ||
| General Efficiency | Overall Avg. | 24 | Jul 1, 2026 | ||
| Code Generation | SWE-Bench | 24 | Jul 1, 2026 | ||
| Mathematical Reasoning | AIME24 | 24 | Jul 1, 2026 | ||
| Mathematical Reasoning | MATH 500 | 24 | Jul 1, 2026 | ||
| Backdoor Detection | Yahoo | 24 | Jul 1, 2026 | ||
| Object existence probing | POPE Adv | 24 | Jul 1, 2026 | ||
| Fine-grained hallucination evaluation | AMBER | 24 | Jul 1, 2026 | ||
| Fairness Evaluation | Fairness Evaluation Suite (BBQ, CrP, GMO, SSt, WnQ) | 24 | Jul 1, 2026 | ||
| Deep Metric Learning | Cars-196 | 24 | Jun 30, 2026 | ||
| Deep Metric Learning | CUB-200-2011 | 24 | Jun 30, 2026 | ||
| Monocular Depth Estimation | Realsee3D Synthetic | 24 | Jun 30, 2026 | ||
| Monocular Depth Estimation | Realsee3D Real | 24 | Jun 30, 2026 | ||
| Instruction following | DollyEval 500 (test) | 24 | Jun 30, 2026 | ||
| Graph Classification | E-Commerce | 24 | Jun 30, 2026 | ||
| Link Prediction | CarPed180K (test) | 24 | Jun 30, 2026 | ||
| Link Prediction | CarPed35K (test) | 24 | Jun 30, 2026 | ||
| Tabular Classification | yeast1 | 24 | Jun 30, 2026 | ||
| Tabular Classification | yeast | 24 | Jun 30, 2026 | ||
| Tabular Classification | Heart Dis. | 24 | Jun 30, 2026 | ||
| Tabular Classification | ecoli 1 | 24 | Jun 30, 2026 | ||
| Tabular Classification | Churn | 24 | Jun 30, 2026 | ||
| Jailbreak Defense | Jailbreak Attack Suite GCG, AutoDAN, DeepInc., Prefill, Int.Laund. | 24 | Jun 30, 2026 |