Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1444 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | SSv2 (train-test) | 21 | May 13, 2026 | ||
| Action Recognition | HMDB51 (train-test) | 21 | May 13, 2026 | ||
| Vulnerable Agent Identification | Battle environment 144 agents, 72 adversaries | 21 | May 13, 2026 | ||
| Vulnerable Agent Identification | Battle environment 64 agents, 32 adversaries | 21 | May 13, 2026 | ||
| Video Temporal Grounding | Charades | 21 | May 13, 2026 | ||
| Exploitability Minimization | Double-Board HUNL | 21 | May 12, 2026 | ||
| Image Synthesis | ImageNet 256x256 | 21 | Jun 5, 2026 | ||
| Segmentation | HAM10000 (Hard Samples) | 21 | May 12, 2026 | ||
| Instruction Following | IFEval | 21 | May 15, 2026 | ||
| Link prediction | BioKG (test) | 21 | May 12, 2026 | ||
| 3D radiotherapy target segmentation | Multimodal 3D radiotherapy target dataset All samples | 21 | May 12, 2026 | ||
| Text-to-Image Generation | Pokémon | 21 | May 29, 2026 | ||
| Pairwise preference evaluation | Common2sense | 21 | May 12, 2026 | ||
| Long-term forecasting | Weather Horizon 96 | 21 | May 15, 2026 | ||
| Audio Deepfake Detection | WaveFake Average (test) | 21 | May 12, 2026 | ||
| Audio Deepfake Detection | WaveFake WaveGlow (test) | 21 | May 12, 2026 | ||
| Audio Deepfake Detection | WaveFake PWG (test) | 21 | May 12, 2026 | ||
| Audio Deepfake Detection | WaveFake HiFi-GAN (test) | 21 | May 12, 2026 | ||
| Audio Deepfake Detection | WaveFake MelGAN (L) (test) | 21 | May 12, 2026 | ||
| Forward PDE Solving | Forward benchmarks 5 PDEs | 21 | May 12, 2026 | ||
| Cross-domain LLM Evaluation | MMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEval | 21 | May 12, 2026 | ||
| MACD Prediction | Finance 30 days | 21 | May 12, 2026 | ||
| MACD Prediction | Finance 7 days | 21 | May 12, 2026 | ||
| Causal Discovery | LR-gaussian-20-20-2 | 21 | May 12, 2026 | ||
| Causal Discovery | LR-gaussian-10-10-2 | 21 | May 12, 2026 |