Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1547 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | OlympiadBench | 20 | Jun 4, 2026 | ||
| Mathematical Reasoning | AMC | 20 | Jun 4, 2026 | ||
| Mathematical Reasoning | AIME 24 | 20 | Jun 4, 2026 | ||
| Multi-task Language Understanding | MMLU | 20 | Jun 4, 2026 | ||
| Question Answering | Concept Questions Open-Ended | 20 | Jun 4, 2026 | ||
| Question Answering | Concept Questions Multiple-Choice | 20 | Jun 4, 2026 | ||
| Web Navigation and Shopping | WebShop (seen) | 20 | Jun 4, 2026 | ||
| Multi-modal Understanding | LLM Evaluation Suite GQA, MMB, MME, POPE, SQA, VQAv2, VQA^Text, VizWiz | 20 | Jun 4, 2026 | ||
| Query Performance Prediction | TREC DL22 | 20 | Jun 4, 2026 | ||
| Query Performance Prediction | TREC DL21 | 20 | Jun 4, 2026 | ||
| Query Performance Prediction | TREC DL 20 | 20 | Jun 4, 2026 | ||
| Query Performance Prediction | TREC DL 19 | 20 | Jun 4, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 20 | Jun 4, 2026 | ||
| LLM Alignment | HHRLHF | 20 | Jun 4, 2026 | ||
| Document Reranking | TREC DL 2019 (test) | 20 | Jun 4, 2026 | ||
| System Prompt Extraction | System Prompt Extraction Out-of-domain SystemCheck and ChatGPT-Prompts | 20 | Jun 4, 2026 | ||
| System Prompt Extraction | System Prompt Extraction In-domain ShareGPT | 20 | Jun 4, 2026 | ||
| Brain network classification | PPMI CN vs Prodromal vs PD (5-fold cross-validation) | 20 | Jun 4, 2026 | ||
| Crystal Structure Prediction | CSP6 | 20 | Jun 4, 2026 | ||
| Severity Classification | Smart Contract Audit Dataset | 20 | Jun 4, 2026 | ||
| Vulnerability Detection | Smart Contract Audit Dataset | 20 | Jun 4, 2026 | ||
| Image Captioning | Flickr30k (val) | 20 | Jun 4, 2026 | ||
| Sentiment Analysis | MOSEI (test) | 20 | Jun 4, 2026 | ||
| Temporal video understanding | TOMATO | 20 | Jun 2, 2026 | ||
| Aggregate Downstream Performance | Aggregate Downstream Performance Suite | 20 | Jun 2, 2026 |