Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1104 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | GSM8K | 25 | May 26, 2026 | ||
| Saliency Prediction | N-UCF Sports | 25 | Jun 15, 2026 | ||
| Saliency Prediction | N-DHF1K | 25 | Jun 15, 2026 | ||
| Knowledge Graph Retrieval | STARK Amazon | 25 | May 29, 2026 | ||
| Knowledge Graph Retrieval | STARK PRIME | 25 | May 29, 2026 | ||
| Watermark Embedding | LLM Prompts | 25 | May 25, 2026 | ||
| Conditional Image Generation | CLEVR | 25 | May 25, 2026 | ||
| Long-context downstream performance | HELMET | 25 | May 25, 2026 | ||
| Long-context downstream performance | LongBench v1 | 25 | May 25, 2026 | ||
| Long-context downstream performance | RULER | 25 | May 25, 2026 | ||
| Instruction Following | IFEval | 25 | May 25, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 25 | May 25, 2026 | ||
| Language Understanding | MMLU | 25 | May 25, 2026 | ||
| Web Task Reasoning | XBench (test) | 25 | May 22, 2026 | ||
| Web Task Reasoning | GAIA (test) | 25 | May 22, 2026 | ||
| Web Task Reasoning | BrowseComp (test) | 25 | May 22, 2026 | ||
| Tabular Reasoning | MultiHier (test) | 25 | May 22, 2026 | ||
| Scientific Reasoning | HLE (test) | 25 | May 22, 2026 | ||
| Scientific Reasoning | SuperGPQA (test) | 25 | May 22, 2026 | ||
| Root-estimation | Fitted Q-regression Experiment 1 (scalar root experiment) (test) | 25 | May 21, 2026 | ||
| Autonomous Driving | NAVSIM v2 (test) | 25 | Jul 1, 2026 | ||
| Causal Discovery (Skeleton recovery) | 1-Factor model | 25 | May 21, 2026 | ||
| Causal Discovery | 1-Factor model | 25 | May 21, 2026 | ||
| Fine-grained Emotion Classification | OV-MERD+ (test) | 25 | May 20, 2026 | ||
| Sentiment Analysis | CH-SIMS v2 (test) | 25 | May 20, 2026 |