Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2353 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment analysis | SIMS v2 (official) | 15 | Jun 29, 2026 | ||
| Sentiment analysis | SIMS (official) | 15 | Jun 29, 2026 | ||
| Sentiment analysis | MOSEI official | 15 | Jun 29, 2026 | ||
| Sentiment analysis | MOSI (official) | 15 | Jun 29, 2026 | ||
| Basic emotion recognition | IEMOCAP (official) | 15 | Jun 29, 2026 | ||
| Basic emotion recognition | MELD (official) | 15 | Jun 29, 2026 | ||
| Basic emotion recognition | MER24 (official) | 15 | Jun 29, 2026 | ||
| Fine-grained emotion recognition | OV-MERD+ | 15 | Jun 29, 2026 | ||
| MaxSim Scoring | L2-normalized FP16 embeddings Nq=32, d=128 | 15 | Jun 26, 2026 | ||
| Image Editing | GEditBench-EN 60 (test) | 15 | Jun 26, 2026 | ||
| Local Descriptor Matching | UBC halfdome (test) | 15 | Jun 26, 2026 | ||
| Local Descriptor Matching | UBC trevi (test) | 15 | Jun 26, 2026 | ||
| Classification | MNIST-10 (test) | 15 | Jun 30, 2026 | ||
| Language Understanding | LAMBADA 8 reasoning tasks | 15 | Jun 26, 2026 | ||
| Information Retrieval and Reading Comprehension | JRT Retrieval Benchmark Suite 1.3B scale, 2K tokens (test) | 15 | Jun 26, 2026 | ||
| Fairness-based Resource Allocation | EF-Allocation | 15 | Jun 26, 2026 | ||
| Medical Visual Question Answering | MedXpertQA OOD (test) | 15 | Jun 26, 2026 | ||
| Pairwise Token Consistency | LibriSpeech clean-100 1.0 (train) | 15 | Jun 26, 2026 | ||
| JPEG Deblocking | Classic5 | 15 | Jun 26, 2026 | ||
| Image Denoising | Urban100 | 15 | Jun 26, 2026 | ||
| Image Denoising | Set12 | 15 | Jun 26, 2026 | ||
| Image Denoising | BSD68 | 15 | Jun 26, 2026 | ||
| Shape Matching | SMAL | 15 | Jun 26, 2026 | ||
| Video Depth Estimation | Sintel 50 frames | 15 | Jul 3, 2026 | ||
| Document Retrieval | Russian-Wikipedia corpus 10^6 documents | 15 | Jun 26, 2026 |