Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 938 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Classification | CORA (test) | 28 | May 8, 2026 | ||
| Node Classification | CHAMELEON | 28 | May 8, 2026 | ||
| Maximum Weight Independent Set (MWIS) | AVR | 28 | May 8, 2026 | ||
| Image Classification | Net | 28 | May 7, 2026 | ||
| Image-Only Editing | CoSTA Image-Only Tasks 1.0 (test) | 28 | May 7, 2026 | ||
| Tabular Classification | 253 Tabular Datasets Average across all shift strengths | 28 | May 7, 2026 | ||
| Tabular Classification | 253 Tabular Datasets Shift strength β=5.0 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 tabular datasets Shift strength β=2.0 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 tabular datasets Shift strength β=1.0 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 tabular datasets Shift strength β=0.5 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 Tabular Datasets Shift strength β=0.1 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 tabular datasets Shift strength β=0.0 | 28 | May 7, 2026 | ||
| Tabular Classification | 253 tabular datasets w/o shift | 28 | May 7, 2026 | ||
| Tabular Classification | OpenML 253 (test) | 28 | May 7, 2026 | ||
| Harmfulness Evaluation | AdvBench | 28 | Jun 16, 2026 | ||
| Hallucination Detection | TriviaQA (40% test) | 28 | May 7, 2026 | ||
| Classification | Dog vs Cat | 28 | May 6, 2026 | ||
| Perceived Valence Classification | AFFEC | 28 | May 6, 2026 | ||
| Perceived Arousal Classification | AFFEC | 28 | May 6, 2026 | ||
| Generalized Category Discovery | StackOverflow (test) | 28 | May 6, 2026 | ||
| Generalized Category Discovery | BANKING (test) | 28 | May 6, 2026 | ||
| Generalized Category Discovery | CLINC (test) | 28 | May 6, 2026 | ||
| Object Manipulation | OGBench cube play (Quadruple) | 28 | Jun 4, 2026 | ||
| General Visual Question Answering | VQA v2 | 28 | Jun 23, 2026 | ||
| AI-generated video detection | EvalCrafter 14 subsets (test) | 28 | May 4, 2026 |