Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1640 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General VQA | HallusionBench | 20 | May 22, 2026 | ||
| STEM & Reasoning | MMMU-Pro | 20 | Jul 7, 2026 | ||
| Temporal Question Answering | TimeQA Easy | 20 | Jun 16, 2026 | ||
| Runtime Agent Memory | HotpotQA | 20 | Feb 26, 2026 | ||
| Runtime Agent Memory | LongMemEval | 20 | Feb 26, 2026 | ||
| Runtime Agent Memory | LoCoMo | 20 | Feb 26, 2026 | ||
| General Performance | Aggregate Across Math, Code, Chat | 20 | Jun 26, 2026 | ||
| Mathematical Reasoning | Math500 | 20 | Feb 26, 2026 | ||
| Reward Modeling | RewardBench 2 | 20 | Mar 5, 2026 | ||
| Code Generation | MBPP | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH | 20 | Feb 26, 2026 | ||
| Language Modeling | LLaMA 13B 2 | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | GAOKAO-en | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC23 | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 24 | 20 | Feb 26, 2026 | ||
| Web-based Agent QA | WebWalkerQA | 20 | Apr 30, 2026 | ||
| LLM Performance Estimation | Winogrande (test) | 20 | Feb 26, 2026 | ||
| LLM Performance Estimation | TruthfulQA (test) | 20 | Feb 26, 2026 | ||
| LLM Performance Estimation | MMLU (test) | 20 | Jun 17, 2026 | ||
| LLM Performance Estimation | HellaSwag (test) | 20 | Feb 26, 2026 | ||
| LLM Performance Estimation | GSM8K (test) | 20 | Feb 26, 2026 | ||
| LLM Performance Estimation | ARC (test) | 20 | Feb 26, 2026 | ||
| Question Answering | TabMWP | 20 | Feb 26, 2026 | ||
| Question Answering | HotpotQA | 20 | Feb 26, 2026 |