Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 988 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Behavior Prediction | Assistant Turns | 27 | Jul 9, 2026 | ||
| Document Retrieval | CMDR-Bench | 27 | Jul 8, 2026 | ||
| 2D Medical Image Segmentation | PMTCXR | 27 | Jul 7, 2026 | ||
| Candidate Retrieval | RecGames 1 | 27 | Jul 7, 2026 | ||
| Candidate Retrieval | RecGames1 | 27 | Jul 7, 2026 | ||
| Overthinking Attack | Fixed image subset | 27 | Jul 3, 2026 | ||
| Model Merging | TED Talks and XLSum 40 sequential tasks (test) | 27 | Jul 2, 2026 | ||
| Quadruped Locomotion | Barkour MJX simulation (test) | 27 | Jul 2, 2026 | ||
| Faithful Calibration | Average across datasets (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG) | 27 | Jul 1, 2026 | ||
| Faithful Calibration | PQA | 27 | Jul 1, 2026 | ||
| Web Navigation | Mind2Web All | 27 | Jun 30, 2026 | ||
| Text-to-Image Generation | DrawBench (200 prompts) | 27 | Jun 30, 2026 | ||
| Tabular Classification | N. Thyroid | 27 | Jun 30, 2026 | ||
| Tabular Classification | glass6 | 27 | Jun 30, 2026 | ||
| Tabular Classification | glass 5 | 27 | Jun 30, 2026 | ||
| Tabular Classification | Flare-F | 27 | Jun 30, 2026 | ||
| Tabular Classification | Fetal Health | 27 | Jun 30, 2026 | ||
| Tabular Classification | ecoli 4 | 27 | Jun 30, 2026 | ||
| Tabular Classification | ecoli2 | 27 | Jun 30, 2026 | ||
| Tabular Classification | Dry Bean | 27 | Jun 30, 2026 | ||
| Truthful Question Answering | TruthfulQA | 27 | Jun 30, 2026 | ||
| Content Injection | Content Injection Scenario | 27 | Jun 30, 2026 | ||
| Over-refusal evaluation | Poisoned GPT4-LLM subset | 27 | Jun 30, 2026 | ||
| Omnidirectional Image Super-Resolution | SUN360 (test) | 27 | Jun 30, 2026 | ||
| Omnidirectional Image Super-Resolution | ODI-SR (test) | 27 | Jun 30, 2026 |