Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1745 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Medical Visual Question Answering | MMMU | 19 | Feb 26, 2026 | ||
| Classification | Sharenting | 19 | Feb 26, 2026 | ||
| Classification | Life events | 19 | Feb 26, 2026 | ||
| Hallucination Detection | Dolly AC LLaMA3-8B | 19 | Feb 26, 2026 | ||
| Hallucination Detection | Dolly AC LLaMA2-13B | 19 | Feb 26, 2026 | ||
| Hallucination Detection | Dolly AC LLaMA2-7B | 19 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth LLaMA3-8B | 19 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth LLaMA2-13B | 19 | Feb 26, 2026 | ||
| Hallucination Detection | RAGTruth LLaMA2-7B | 19 | Feb 26, 2026 | ||
| Hallucination detection | llava | 19 | Feb 26, 2026 | ||
| Hallucination detection | mscoco | 19 | Feb 26, 2026 | ||
| Software Engineering | SWE-Bench Pro (public) | 19 | Jun 12, 2026 | ||
| Summarization | TrueBrief (test) | 19 | Feb 26, 2026 | ||
| Long Story Evaluation | LongStoryEval Full (test) | 19 | Feb 26, 2026 | ||
| Competitive Programming | LiveCodeBench 2408 - 2505 v6 | 19 | Feb 26, 2026 | ||
| Annotator Modeling | AITA situation | 19 | Feb 26, 2026 | ||
| Information-Seeking | BrowseComp Chinese (full) | 19 | Feb 26, 2026 | ||
| Depressive symptom classification | RESTOREx (test) | 19 | Feb 26, 2026 | ||
| Multi-turn tool calling | τ2-bench | 19 | May 1, 2026 | ||
| Memory Extraction | HaluMem | 19 | Jun 25, 2026 | ||
| Social Intelligence Analysis | SocialBench (test) | 19 | Feb 26, 2026 | ||
| Opinion Summarization | Rotten Tomatoes (full dataset) | 19 | Feb 26, 2026 | ||
| General Knowledge | SuperGPQA | 19 | Mar 4, 2026 | ||
| Emotion recognition in conversation | CHERMA | 19 | May 20, 2026 | ||
| Tool Use Evaluation | ToolSandbox | 19 | Apr 8, 2026 |