Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2140 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instruction Following | Alpaca GPT4 | 16 | Jun 4, 2026 | ||
| Blind Lens Aberration Correction | RealLens-Sim (MA) | 16 | Jun 4, 2026 | ||
| Visual Odometry | NCLT | 16 | Jun 4, 2026 | ||
| Transmission Expansion Planning | Transmission Network MCS scenario | 16 | Jun 4, 2026 | ||
| Multimodal Judgment | MM-Vet | 16 | Jun 2, 2026 | ||
| Multimodal Judgment | C.C. | 16 | Jun 2, 2026 | ||
| Multimodal Judgment | COCO | 16 | Jun 2, 2026 | ||
| 3D human reconstruction | 2K2K (test) | 16 | Jun 2, 2026 | ||
| 3D human reconstruction | THuman2 (test) | 16 | Jun 2, 2026 | ||
| 3D human reconstruction | CustomHuman (test) | 16 | Jun 2, 2026 | ||
| Complex Tasks | BrowseComp+ Complex Tasks 2nd Pass | 16 | Jun 2, 2026 | ||
| Complex Tasks | BrowseComp+ Complex Tasks 1st Pass | 16 | Jun 2, 2026 | ||
| Code Generation | BigCodeBench Lite-Pro Naive Stream | 16 | Jun 2, 2026 | ||
| Click-Through Rate Prediction | Agentic AI Message Dataset (test) | 16 | Jun 2, 2026 | ||
| Reasoning | GPQA Diamond | 16 | Jun 2, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 16 | Jun 2, 2026 | ||
| Mathematical Reasoning | AIME 2023-2025 macro-average | 16 | Jun 2, 2026 | ||
| Video Understanding | MLVU | 16 | Jul 7, 2026 | ||
| Certified Image Classification | Tiny ImageNet epsilon=1/255 (test) | 16 | Jun 2, 2026 | ||
| Certified Image Classification | CIFAR-10 epsilon=2/255 (test) | 16 | Jun 2, 2026 | ||
| Jailbreak Attack Evaluation | SafetyBench MCV | 16 | Jun 2, 2026 | ||
| Conversation | MT-Bench | 16 | Jun 2, 2026 | ||
| Mathematical reasoning | GSM8K | 16 | Jun 11, 2026 | ||
| Mathematical Reasoning | AIME 2026 | 16 | Jun 16, 2026 | ||
| Continual Learning | NI-Seq-M2 | 16 | Jun 2, 2026 |