Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2114 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Code Simulation | CruxEval-I | 16 | Jun 25, 2026 | ||
| Logical Reasoning | ARC-AGI | 16 | Jun 25, 2026 | ||
| Image Classification | CIFAR-100 (test) | 16 | Jun 25, 2026 | ||
| Image Synthesis | NANO-TEM synthetic samples n=6656 | 16 | Jun 24, 2026 | ||
| 3D Visual Grounding | ScanRefer 10 (val) | 16 | Jun 24, 2026 | ||
| Fault Attribution | TRAIL SWEBench 31 traces | 16 | Jun 24, 2026 | ||
| Fault Attribution | TRAIL (GAIA) 117 traces | 16 | Jun 24, 2026 | ||
| Fault attribution | Who&When Hand (58 traces) | 16 | Jun 24, 2026 | ||
| Fault attribution | Who&When Algo (126 traces) | 16 | Jun 24, 2026 | ||
| Video Question Answering | ViTexQA | 16 | Jun 24, 2026 | ||
| Language Agent Interaction | AgentWorldBench main results rubric mean | 16 | Jun 24, 2026 | ||
| Object Hallucination Evaluation | POPE | 16 | Jun 24, 2026 | ||
| Multimodal Understanding | Multimodal Evaluation Suite GQA, MMBench, MMBench-CN, MME, POPE, ScienceQA, TextVQA (various) | 16 | Jun 24, 2026 | ||
| Text Localization | DocLocal4K | 16 | Jun 24, 2026 | ||
| Depression Prediction | Depression Prediction dataset 1.0 (test) | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | CASIA v2 | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | FKG-50K Overall | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | FKG-50K Trad-Edit | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | FKG-50K Splicing | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | FKG-50K Full AI | 16 | Jun 24, 2026 | ||
| Fake and manipulated image detection | FKG-50K AI-Edit | 16 | Jun 24, 2026 | ||
| B-cell epitope discovery | SAbDab September 23, 2023 (test) | 16 | Jun 24, 2026 | ||
| Text Classification | MR | 16 | Jun 24, 2026 | ||
| Causal-order reasoning | VCR-Causal | 16 | Jun 24, 2026 | ||
| Causal-order reasoning | VQA-Causal | 16 | Jun 24, 2026 |