Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 815 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AGIEval-MATH (test) | 31 | May 12, 2026 | ||
| Mathematical reasoning | MATH-500 | 31 | May 29, 2026 | ||
| Multiple Choice Question Answering | Average (OBQA, ARC, Riddle, PQA) | 31 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | RiddleSense | 31 | Feb 26, 2026 | ||
| Multi-Hop Question Answering | HotpotQA | 31 | Feb 26, 2026 | ||
| Automatic Speech Recognition | AISHELL-1 | 31 | May 1, 2026 | ||
| Data Science Agent tasks | xBench-DS | 31 | Mar 10, 2026 | ||
| Knowledge Tracing | ASSISTments 2017 | 31 | Jun 15, 2026 | ||
| Modal Retrieval | Ele-fashion | 31 | Mar 31, 2026 | ||
| Graduate-level Reasoning | GPQA | 31 | Jun 11, 2026 | ||
| Multi-hop Question Answering | HotpotQA (val) | 31 | Mar 17, 2026 | ||
| Classification | ABCD-ADHD | 31 | May 8, 2026 | ||
| Code Generation | LiveCodeBench v5 | 31 | Jun 18, 2026 | ||
| Interactive Reasoning | ScienceWorld (Seen) | 31 | Feb 26, 2026 | ||
| Hallucination Detection | AQuA | 31 | Feb 26, 2026 | ||
| Mathematical Reasoning | GeoQA (test) | 31 | Feb 26, 2026 | ||
| General Knowledge | MMLU | 31 | Apr 28, 2026 | ||
| Multimodal Understanding | MMT-Bench | 31 | Jun 9, 2026 | ||
| Instruction Following | Arena Hard v0.1 | 31 | Jun 11, 2026 | ||
| Multilingual Knowledge Evaluation | M-MMLU | 31 | Mar 18, 2026 | ||
| Tool Calling | Tool-Alpaca | 31 | Feb 26, 2026 | ||
| Long-context understanding | InfiniteBench v1 (test) | 31 | Feb 26, 2026 | ||
| Image Classification | 8 Vision Tasks Aggregate ViT-B/32 ViT-L/14 (average) | 31 | Feb 26, 2026 | ||
| Information Retrieval | ArguAna | 31 | May 29, 2026 | ||
| Moving Object Segmentation | FBMS-59 | 31 | Jun 30, 2026 |