Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1492 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-context language understanding | RULER 16k context length | 21 | May 13, 2026 | ||
| General Reasoning | HLE | 21 | Feb 26, 2026 | ||
| Multilingual Language Understanding | MMMLU (Massive Multilingual Language Understanding) | 21 | Feb 26, 2026 | ||
| Question Answering | Average (SQuAD, NewsQA, TriviaQA, NQ, HotpotQA) | 21 | Feb 26, 2026 | ||
| Question Answering | HotpotQA | 21 | Feb 26, 2026 | ||
| Question Answering | NQ | 21 | Feb 26, 2026 | ||
| Question Answering | TriviaQA | 21 | Feb 26, 2026 | ||
| Question Answering | SQuAD | 21 | Feb 26, 2026 | ||
| Zero-shot reasoning | benchmark datasets (PIQA, HeSw, ARC-e, ARC-c, OBQA, Race, WSC273, LAMBADA, MMLU) Zero-shot | 21 | Feb 26, 2026 | ||
| SOP Understanding | SOPBench (test) | 21 | Feb 26, 2026 | ||
| Clinical Text-to-SQL | EpiAskKB 2025 (test) | 21 | Feb 26, 2026 | ||
| Mathematical Reasoning | Beyond AIME | 21 | Feb 26, 2026 | ||
| Unsafe content detection | LlavaGuard | 21 | Jul 2, 2026 | ||
| Offline Bin Packing Problem | Offline BPP | 21 | Feb 26, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP | 21 | Feb 26, 2026 | ||
| Traveling Salesman Problem | TSP | 21 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTh2 -> ETTm1 (test) | 21 | Apr 15, 2026 | ||
| Robotic Arm Manipulation | MetaWorld Very Hard | 21 | May 13, 2026 | ||
| Medical Question Answering | MedXpert (test) | 21 | Jun 26, 2026 | ||
| Multi-dimensional Knapsack Problem | MKP N=100, m=5 | 21 | Feb 26, 2026 | ||
| Content Moderation | Aegis 2.0 | 21 | Apr 7, 2026 | ||
| Chemical Reaction Prediction | USPTO50k | 21 | Mar 4, 2026 | ||
| Scientific and General Reasoning | GPQA Diamond | 21 | Feb 26, 2026 | ||
| Scientific and General Reasoning | MMLU Pro | 21 | Feb 26, 2026 | ||
| Reasoning | GSM8k | 21 | Feb 26, 2026 |