Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1569 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sparse Autoencoder Evaluation | Gemma-2-2B activations | 20 | May 8, 2026 | ||
| Multi-task regression | LRGB peptides-struct (test) | 20 | May 8, 2026 | ||
| Binary classification | Default | 20 | May 29, 2026 | ||
| Classification | CPT zero-shot | 20 | May 8, 2026 | ||
| Mathematical Reasoning | AIME 24 | 20 | May 8, 2026 | ||
| Mathematical Reasoning | AMC 23 | 20 | May 8, 2026 | ||
| Mathematical Reasoning | Minerva | 20 | May 8, 2026 | ||
| Mathematical Reasoning | Olympiad | 20 | May 8, 2026 | ||
| Hallucination detection | Average (CoQA, SQuAD v2.0, TriviaQA, TruthfulQA) | 20 | May 8, 2026 | ||
| Hallucination detection | SQuAD v2.0 | 20 | May 8, 2026 | ||
| Hallucination detection | CoQA | 20 | May 8, 2026 | ||
| Object Detection | PASCALRAW Normal | 20 | May 11, 2026 | ||
| Expert-level Reasoning | GPQA Diamond | 20 | Jul 7, 2026 | ||
| Reliability Estimation | BioASQ | 20 | May 8, 2026 | ||
| Reliability Estimation | TruthfulQA | 20 | May 8, 2026 | ||
| Question Answering | 2WikiMultihopQA | 20 | May 8, 2026 | ||
| Robot Manipulation | RoboCasa GR1 | 20 | May 29, 2026 | ||
| Time series prediction | ETT (val) | 20 | May 8, 2026 | ||
| Time series prediction | BoC (val) | 20 | May 8, 2026 | ||
| Time series prediction | BoC | 20 | May 8, 2026 | ||
| Time series prediction | Logistic | 20 | May 8, 2026 | ||
| Time series prediction | Periodic | 20 | May 8, 2026 | ||
| Protein hit discovery | ChEMBL Proteins | 20 | May 8, 2026 | ||
| Surrogate detection under model extraction attack | Computers | 20 | May 8, 2026 | ||
| Surrogate detection under model extraction attack | CIFAR | 20 | May 8, 2026 |