Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1219 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Memory Control Flow Attack (Cross-task Propagation) | MEMFLOW M-Scope | 24 | Mar 17, 2026 | ||
| LLM Alignment | AlpacaEval | 24 | May 11, 2026 | ||
| Image Retrieval | THINGS-EEG (test) | 24 | Jun 16, 2026 | ||
| Localization | CAMELYON17 Center 2 | 24 | May 1, 2026 | ||
| Localization | CAMELYON17 Center 1 | 24 | May 1, 2026 | ||
| Localization | CAMELYON17 Center 0 | 24 | May 1, 2026 | ||
| Speech Enhancement | DNS Challenge With Reverb (test) | 24 | Apr 15, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 | 24 | May 20, 2026 | ||
| Segmentation | PAV-SOD 35 (test) | 24 | Mar 16, 2026 | ||
| Instance Segmentation | HunyuanWorld 1.0 | 24 | Mar 16, 2026 | ||
| Trajectory Planning | nuPlan 14-Hard (test) | 24 | Jun 2, 2026 | ||
| Robotic Manipulation | SimplerEnv WidowX v1 (test) | 24 | Jun 4, 2026 | ||
| General Reasoning | Overall MATH-500 AIME25 HumanEval GPQA | 24 | Mar 16, 2026 | ||
| AI Text Detection | HC3 AI-Prob | 24 | Mar 16, 2026 | ||
| Sentiment Analysis | SST-2 | 24 | Mar 16, 2026 | ||
| Safety prediction | Donkey Car | 24 | Mar 16, 2026 | ||
| Safety prediction | Cart Pole | 24 | Mar 16, 2026 | ||
| Safety prediction | Racing Car | 24 | Mar 16, 2026 | ||
| Navigation | Navigation | 24 | May 14, 2026 | ||
| Multimodal Agent Task | MMSearch-Plus | 24 | Mar 13, 2026 | ||
| Multimodal Agent Task | TIR-Bench | 24 | Mar 13, 2026 | ||
| Conditional generation | MS-COCO 512x512 (val) | 24 | Mar 13, 2026 | ||
| Conditional Image Generation | MS-COCO 512 x 512 1.5 | 24 | Mar 13, 2026 | ||
| Unconditional Image Generation | AFHQ 64 x 64 v2 (train test) | 24 | Mar 13, 2026 | ||
| Text-to-Image Generation | COCO 512x512 | 24 | Mar 13, 2026 |