Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1463 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | HE 50% corrupted features noise | 21 | Mar 24, 2026 | ||
| Classification | GE 50% corrupted features (50% noise) | 21 | Mar 24, 2026 | ||
| Classification | EY 50% corrupted features (50% noise) | 21 | Mar 24, 2026 | ||
| Classification | CO 50% corrupted features | 21 | Mar 24, 2026 | ||
| Regression | CH 50% corrupted features (50% noise) | 21 | Mar 24, 2026 | ||
| Node Classification | arxiv | 21 | Mar 24, 2026 | ||
| Node Classification | Pubmed | 21 | Mar 24, 2026 | ||
| Node Classification | Cora | 21 | Mar 24, 2026 | ||
| Goal-conditioned navigation | GOAT-Bench | 21 | Jun 24, 2026 | ||
| Causal Effect Estimation | Flickr (in-sample) | 21 | Mar 24, 2026 | ||
| Causal Effect Estimation | BlogCatalog simulated (In-sample) | 21 | Mar 24, 2026 | ||
| Causal Effect Estimation | Flickr 1.0 (out-of-sample) | 21 | Mar 24, 2026 | ||
| Causal Effect Estimation | BlogCatalog (out-of-sample) | 21 | Mar 24, 2026 | ||
| LLM Jailbreaking | JBB-Behaviors Scenario J3 | 21 | Mar 23, 2026 | ||
| LLM Jailbreaking | JBB-Behaviors Scenario J2 | 21 | Mar 23, 2026 | ||
| LLM Jailbreaking | JBB-Behaviors Scenario J1 | 21 | Mar 23, 2026 | ||
| LLM Jailbreaking | GPTFuzzer Scenario G3 | 21 | Mar 23, 2026 | ||
| LLM Jailbreaking | GPTFuzzer Scenario G2 | 21 | Mar 23, 2026 | ||
| LLM Jailbreaking | GPTFuzzer Scenario G1 | 21 | Mar 23, 2026 | ||
| Image Classification | Waterbirds 100% correlation (test) | 21 | May 13, 2026 | ||
| Person Re-identification | LPW s2 | 21 | May 7, 2026 | ||
| Person Re-identification | LPW | 21 | May 7, 2026 | ||
| 3D Scene Compression | 3D Scene Compression Performance | 21 | Mar 23, 2026 | ||
| Novel View Synthesis | Deep Blending | 21 | May 12, 2026 | ||
| Multiple Choice Question Answering | SuperGPQA MCQA | 21 | May 25, 2026 |