Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1361 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Conversational Question Answering | CoQA | 22 | Apr 29, 2026 | ||
| Question Answering | TruthfulQA | 22 | Apr 29, 2026 | ||
| Summarization | CNN DailyMail | 22 | Apr 29, 2026 | ||
| Continual Learning | MNIST Shuffled Labels | 22 | May 1, 2026 | ||
| Image Classification | Tiny-ImageNet | 22 | Apr 28, 2026 | ||
| One-year clinical instability after initial heart failure diagnosis | Swedish heart failure cohort | 22 | Apr 28, 2026 | ||
| Clustering Evaluation | MNIST 10,000 random samples | 22 | Apr 28, 2026 | ||
| Scientific Text Classification | FORC without ORKG taxonomy hierarchy | 22 | Apr 28, 2026 | ||
| Audio-to-Text Retrieval | AudioCaps | 22 | Apr 28, 2026 | ||
| Regression | Kin8nm | 22 | Apr 28, 2026 | ||
| Attribute Steering | HelpSteer | 22 | Apr 28, 2026 | ||
| Refusal Behavior | Refusal | 22 | Apr 28, 2026 | ||
| Question Answering | TruthfulQA | 22 | Apr 28, 2026 | ||
| Point Cloud Edge Extraction | ABC All | 22 | Apr 27, 2026 | ||
| Electricity Price Forecasting | Electricity Price (test) | 22 | Jun 11, 2026 | ||
| Constraint discovery from data-code pairs | ICDBench | 22 | Apr 24, 2026 | ||
| Delayed Conversion Modeling | Taobao | 22 | Apr 28, 2026 | ||
| Optimization Problem Solving | OptiVerse | 22 | Apr 24, 2026 | ||
| Choice-based Visual Question Answering | EgoPoint-Bench real-world 1.0 (test) | 22 | Apr 24, 2026 | ||
| Choice-based Visual Question Answering | EgoPoint-Bench simulation 1.0 (test) | 22 | Apr 24, 2026 | ||
| Math Reasoning | AIME24 | 22 | Apr 24, 2026 | ||
| Diagnostic Classification | ABIDE-I AAL116 atlas | 22 | Apr 24, 2026 | ||
| Graph Reconstruction | Cora | 22 | Apr 24, 2026 | ||
| Fine-grained Video Understanding | VCG-Bench | 22 | Apr 24, 2026 | ||
| Fine-grained Video Understanding | VideoComp | 22 | Apr 24, 2026 |