Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2223 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Estimation | Example 2 rho=0.75 | 16 | Mar 9, 2026 | ||
| Estimation | Example 2 rho=0.5 | 16 | Mar 9, 2026 | ||
| Audio Deepfake Detection | ASVspoof 2024 | 16 | Apr 16, 2026 | ||
| Person Re-Identification | SAvg Cross-domain Average | 16 | Mar 9, 2026 | ||
| VFX Generation | OpenVFX | 16 | Mar 9, 2026 | ||
| Multi-Session Place Recognition | NCLT 26→20 V-32 | 16 | Mar 9, 2026 | ||
| Action Recognition | NTU-60 (C-view) | 16 | Mar 9, 2026 | ||
| Medical Image Segmentation | ACDC | 16 | Mar 9, 2026 | ||
| Robot Manipulation | Panda-Gym (OOD) | 16 | Mar 9, 2026 | ||
| Robot Manipulation | Panda-Gym In-Distribution | 16 | Mar 9, 2026 | ||
| Emotion and speaker adaptation | Chinese speech data (test) | 16 | Mar 9, 2026 | ||
| Text Generation | FuseEval English Scenario | 16 | Mar 9, 2026 | ||
| LLM Evaluation | AlpacaEval 2.0 | 16 | Jul 7, 2026 | ||
| Fact-Checking | PolitiFact | 16 | Jun 29, 2026 | ||
| Response Ranking | ParaS2SBench | 16 | Mar 9, 2026 | ||
| Paralinguistic-aware dialogue | ParaS2SBench Synthetic (Human Evaluation) | 16 | Mar 9, 2026 | ||
| Text Embedding | AfriMTEB (AMH, GAZ, HAU, IBO, KIN, SWA, XHO, YOR, ZUL) Lite (test) | 16 | Mar 9, 2026 | ||
| Molecular Classification | Molecular Classification Subset V | 16 | Mar 6, 2026 | ||
| Molecular Classification | Molecular tasks no-validation | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 24 | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 23 | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 22 | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 21 | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 20 | 16 | Mar 6, 2026 | ||
| Molecular classification | Task 19 | 16 | Mar 6, 2026 |