Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1939 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Grounding accuracy | Fakepedia-MH (test) | 18 | Feb 26, 2026 | ||
| Grounding accuracy | Fakepedia (FP) (test) | 18 | Feb 26, 2026 | ||
| Code Generation | APPS Overall | 18 | Feb 27, 2026 | ||
| Commonsense Reasoning | WG-M | 18 | Feb 26, 2026 | ||
| Multimodal Image Fusion | M3FD (test) | 18 | Jun 11, 2026 | ||
| Certified Robustness | CIFAR-10 l2 (test) | 18 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Walker Gym-MuJoCo Medium-Expert D4RL | 18 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | HalfCheetah Medium-Expert Gym-MuJoCo D4RL | 18 | Feb 26, 2026 | ||
| 3D Object Classification | ShapeNet v2 | 18 | Jun 18, 2026 | ||
| Summarization | CNN | 18 | Feb 26, 2026 | ||
| Summarization | MeetingBank | 18 | Feb 26, 2026 | ||
| Summarization | CNN | 18 | Feb 26, 2026 | ||
| Summarization | ACI-Bench | 18 | Feb 26, 2026 | ||
| Summarization | CNN | 18 | Feb 26, 2026 | ||
| Summarization | ACI-Bench (test) | 18 | Feb 26, 2026 | ||
| Instruction Tuning | IT Evaluation Suite MMLU, BBH, GSM, TydiQA, CodeX, AE | 18 | Feb 26, 2026 | ||
| Image Fitting | AFHQ (test) | 18 | Apr 1, 2026 | ||
| Image Fitting | CelebA-HQ (test) | 18 | Apr 1, 2026 | ||
| Multimodal Reasoning | AI2D | 18 | Jun 9, 2026 | ||
| Surface Normal Estimation | ScanNet Normal Benchmark (test) | 18 | Feb 26, 2026 | ||
| RGBT Tracking | LasHeR | 18 | Feb 26, 2026 | ||
| Implicit Video Representation | UVG-HD full 1920x1080 | 18 | Feb 26, 2026 | ||
| Image Generation | FFHQ 64x64 (train test) | 18 | Apr 27, 2026 | ||
| Shadow Removal | INS synthetic (test) | 18 | Feb 26, 2026 | ||
| Image Rescaling | DIV2K (test) | 18 | Feb 26, 2026 |