Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1885 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| GPU kernel code generation and optimization | KernelBench Level 1 (test) | 18 | Mar 4, 2026 | ||
| Visual Mathematical Reasoning | MathVista 1.0 (testmini) | 18 | Mar 4, 2026 | ||
| Text-to-Image Generation | GenEval | 18 | Mar 4, 2026 | ||
| Clustering | ClusTREC-Covid | 18 | Mar 4, 2026 | ||
| Clustering | MedrxivClustering S2S | 18 | Mar 4, 2026 | ||
| Clustering | MedrxivClusteringP2P (MedP2P) | 18 | Mar 4, 2026 | ||
| Clustering | BiorxivClustering S2S | 18 | Mar 4, 2026 | ||
| Information Retrieval | R2-PMC | 18 | Mar 4, 2026 | ||
| Information Retrieval | R2-IYI | 18 | Mar 4, 2026 | ||
| Information Retrieval | PHQA | 18 | Mar 4, 2026 | ||
| Response Moderation | FlexBench | 18 | Mar 4, 2026 | ||
| Humanoid Motion Tracking | MoCap Data AMASS+LAFAN1 | 18 | Mar 4, 2026 | ||
| Mathematical Reasoning | TheoremQA | 18 | Mar 4, 2026 | ||
| Mathematical Reasoning | Olympia | 18 | Mar 4, 2026 | ||
| Mathematical Reasoning | DM-Math | 18 | Mar 4, 2026 | ||
| Correctness Prediction | Medals | 18 | Mar 4, 2026 | ||
| Correctness Prediction | Math operations | 18 | Mar 4, 2026 | ||
| Correctness Prediction | Cities | 18 | Mar 4, 2026 | ||
| Correctness Prediction | Notable People | 18 | Mar 4, 2026 | ||
| Multimodal Understanding | High-IC tasks MMB, POPE, MME, SEED, GQA, TextVQA LLaVA-NeXT-7B | 18 | Mar 4, 2026 | ||
| Multimodal Understanding | LLaVA High-IC tasks (MMB, POPE, MME, SEED, GQA) 1.5-7B | 18 | Mar 4, 2026 | ||
| Image Classification | Fashion-MNIST heterogeneous (test) | 18 | Mar 4, 2026 | ||
| Image Classification | MNIST 100 clients, highly heterog. (test) | 18 | Mar 4, 2026 | ||
| Multimodal Mathematical Reasoning | WeMath mini (test) | 18 | May 6, 2026 | ||
| Link Prediction | WikiArt MKG v2 | 18 | Mar 4, 2026 |