Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1053 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Offline Reinforcement Learning | OGBench puzzle-4x4 | 26 | May 12, 2026 | ||
| Visual Object Tracking | EventVOT (test) | 26 | May 8, 2026 | ||
| Image Classification | Flower102 | 26 | May 8, 2026 | ||
| Next-POI Prediction | TKY | 26 | May 8, 2026 | ||
| Emotion Recognition | DEAP | 26 | Jul 2, 2026 | ||
| Evidence Retrieval | FAKEWIKI Indirect | 26 | May 8, 2026 | ||
| Evidence Retrieval | FAKEWIKI NoiseInjection | 26 | May 8, 2026 | ||
| Evidence Retrieval | FAKEWIKI RolePlay | 26 | May 8, 2026 | ||
| Evidence Retrieval | FAKEWIKI Obfuscate | 26 | May 8, 2026 | ||
| Evidence Retrieval | FAKEWIKI Clean | 26 | May 8, 2026 | ||
| Hallucination | HallusionBench | 26 | Jun 16, 2026 | ||
| Classification Calibration | MultiCorrupt nuScenes v1.0-trainval (val) | 26 | May 8, 2026 | ||
| Stage 2 region-specific track classification | AoA features 2000 snapshots NLoS | 26 | May 7, 2026 | ||
| Stage 2 region-specific track classification | AoA features LoS 2000 snapshots | 26 | May 7, 2026 | ||
| Membership Inference Attack | SQuADShifts (test) | 26 | May 7, 2026 | ||
| Object Navigation | MP3D (val) | 26 | Jun 11, 2026 | ||
| Logical Reasoning | RP LP Domain, Npred ≤ 30, δ ≤ 6 | 26 | May 7, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 In-Distribution | 26 | May 8, 2026 | ||
| Language Modeling | Language Modeling Evaluation | 26 | Jun 4, 2026 | ||
| Multimodal Synthesis | PolyMNIST | 26 | May 4, 2026 | ||
| Knowledge Unlearning | WMDP | 26 | May 4, 2026 | ||
| Essay Grading | Essay Grading (test) | 26 | May 4, 2026 | ||
| Pairwise RAG Comparison | Pairwise RAG Comparison (test) | 26 | May 4, 2026 | ||
| Mathematical Error Detection | Mathematical Error Detection (test) | 26 | May 4, 2026 | ||
| Image Denoising | Set12 | 26 | May 1, 2026 |