Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1480 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Music Source Separation | MUSDB18 HQ | 21 | Feb 26, 2026 | ||
| Speech Reconstruction | SeedTTS en (test) | 21 | Jun 11, 2026 | ||
| LiDAR-Camera Calibration | Solid-state LiDAR and Pinhole Camera | 21 | Feb 26, 2026 | ||
| LiDAR-Camera Calibration | Solid-state LiDAR and Full Frame Camera | 21 | Feb 26, 2026 | ||
| Robotic Grasping | ReOcS (normal-hard) | 21 | Feb 26, 2026 | ||
| Robot Manipulation | SimplerEnv OOD | 21 | May 29, 2026 | ||
| Pick-and-place | SIMPLER-WidowX | 21 | Jul 7, 2026 | ||
| End-to-end driving | LangAuto Tiny | 21 | Mar 10, 2026 | ||
| End-to-end driving | LangAuto Short | 21 | Mar 10, 2026 | ||
| Object Goal Navigation | HM3D (val) | 21 | Feb 26, 2026 | ||
| Classification | HIGGS (test) | 21 | Jun 11, 2026 | ||
| Multi-task Evaluation | Aggregate (AIME25, AIME24, MATH, GSM8K, HumanEval+, MBPP+, MedQA, GPQA-Diamond) | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 21 | Feb 26, 2026 | ||
| Image Classification | TinyImageNet (test) | 21 | Feb 26, 2026 | ||
| Domain-incremental Learning | CDDB | 21 | Apr 3, 2026 | ||
| Question Answering | MMLU, TruthfulQA, and BBQ | 21 | May 20, 2026 | ||
| Class Incremental Learning | ImageNet-100 B50 Inc10 | 21 | May 11, 2026 | ||
| Image Generation | ImageNet 256x256 50k (test) | 21 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Hopper random | 21 | May 7, 2026 | ||
| Mathematical Reasoning | Reasoning Datasets Average (MATH500, OlympiadBench, MinervaMath, GSM8K, MMLU) | 21 | Feb 26, 2026 | ||
| Remaining Useful Life Estimation | PRONOSTIA 100Hz4.2kN | 21 | Feb 26, 2026 | ||
| Remaining Useful Life Estimation | PRONOSTIA 100Hz4kN | 21 | Feb 26, 2026 | ||
| Aggregate Performance | Multi-task Evaluation Suite | 21 | Feb 26, 2026 | ||
| Science Question Answering | GPQA | 21 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 21 | Feb 26, 2026 |