Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2133 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME 2025 | 16 | Jun 11, 2026 | ||
| Helpfulness | HH-RLHF | 16 | Jun 9, 2026 | ||
| Video Temporal Grounding | ActivityNet | 16 | Jun 9, 2026 | ||
| Video Question Answering | Sports-QA (test) | 16 | Jun 9, 2026 | ||
| Human Preference Alignment | Arena-Hard | 16 | Jun 9, 2026 | ||
| Implicit Content Detection | ChLGBT Implicit (test) | 16 | Jun 9, 2026 | ||
| Portfolio Management | DJIA 29 constituents 2014-2024 (test) | 16 | Jun 9, 2026 | ||
| Document Question Answering | LongDocURL (test) | 16 | Jun 9, 2026 | ||
| Document Question Answering | MMLongBench-Doc (test) | 16 | Jun 9, 2026 | ||
| Mathematics | HMMT 2026 | 16 | Jun 23, 2026 | ||
| General Reasoning | Reasoning Benchmarks Average | 16 | Jun 9, 2026 | ||
| Image Classification | CIFAR-100 1.0 (Fourth Session Transition) | 16 | Jun 9, 2026 | ||
| Image Classification | CIFAR-100 Second Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | CIFAR-10 Fourth Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | CIFAR-10 Second Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | SVHN Fourth Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | SVHN Second Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | FMNIST Fourth Session Transition 1.0 | 16 | Jun 9, 2026 | ||
| Image Classification | FMNIST 1.0 (Second Session Transition) | 16 | Jun 9, 2026 | ||
| Image Classification | MNIST 1.0 (Fourth Session Transition) | 16 | Jun 9, 2026 | ||
| Image Classification | MNIST 1.0 (Second Session Transition) | 16 | Jun 9, 2026 | ||
| Inference Performance Evaluation | GPU timing experiment 2K-8K context lengths | 16 | Jun 9, 2026 | ||
| Ontology Concept Labeling Evaluation | Trials Ingredient, Pizza, and Pizzeria lattices 14 and 15 | 16 | Jun 9, 2026 | ||
| Multi-agent coordination | Overcooked-AI Mean of CR/AA/Ring/FC/CC layouts | 16 | Jun 9, 2026 | ||
| Mixture-proportion estimation | DLBCL flow-cytometry raw (two manual-gated cell populations) | 16 | Jun 9, 2026 |