Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1579 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reasoning | BRUMO25 | 20 | Apr 20, 2026 | ||
| Reasoning | AIME 25 | 20 | Apr 20, 2026 | ||
| Reasoning | AIME 24 | 20 | Apr 20, 2026 | ||
| Bias Reduction Estimation | COVID-19 vaccine preference dataset m=150 samples | 20 | Apr 20, 2026 | ||
| Bias Reduction Estimation | COVID-19 vaccine preference dataset m=50 samples | 20 | Apr 20, 2026 | ||
| Out-of-Distribution Detection | CIFAR 100 Far OOD | 20 | May 28, 2026 | ||
| Out-of-Distribution Detection | CIFAR 10 (Far OOD) | 20 | May 28, 2026 | ||
| Text-based Game Playing | J-TTL Jericho (test-time learning) | 20 | Apr 20, 2026 | ||
| Question Answering | ARC Easy | 20 | May 12, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 20 | Apr 16, 2026 | ||
| Mathematical Reasoning | GSM8K | 20 | Apr 16, 2026 | ||
| Logical Reasoning | FLD | 20 | Apr 16, 2026 | ||
| Continual Instruction Tuning | MLLM-DCL | 20 | Apr 16, 2026 | ||
| Supervised Fine-Tuning | Heterogeneous SFT Benchmarks (Evaluation) | 20 | Apr 16, 2026 | ||
| Perturbation response modeling | Srivatsan20 | 20 | Apr 16, 2026 | ||
| Perturbation response modelling | Norman19 | 20 | Apr 16, 2026 | ||
| Planning in ACNO-MDPs | Frozen Lake 8x8 | 20 | Apr 16, 2026 | ||
| Planning in ACNO-MDPs | Frozen Lake 4x4 Hard | 20 | Apr 16, 2026 | ||
| Planning in ACNO-MDPs | Frozen Lake 4x4 Default | 20 | Apr 16, 2026 | ||
| Mathematical Reasoning | Minerva-Math | 20 | Apr 16, 2026 | ||
| Mathematical Reasoning | MATH 500 | 20 | Apr 16, 2026 | ||
| Binary Classification | 4DBInfer (test) | 20 | Jul 8, 2026 | ||
| Budget Allocation | Twin-2K 500 reps | 20 | Apr 15, 2026 | ||
| Pansharpening | WorldView-2 reduced-resolution (test) | 20 | May 19, 2026 | ||
| Movie Dubbing | CelebV-Dub Setting 2 | 20 | Apr 15, 2026 |