Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 814 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Vessel Segmentation | XCAV (test) | 31 | Mar 4, 2026 | ||
| Hallucination Evaluation | POPE Adversarial v1.0 (test) | 31 | Feb 26, 2026 | ||
| Hallucination Evaluation | POPE Popular v1.0 (test) | 31 | Feb 26, 2026 | ||
| Hallucination Evaluation | POPE Random v1.0 (test) | 31 | Feb 26, 2026 | ||
| Image Classification | ImageNet V | 31 | Feb 26, 2026 | ||
| Commonsense Reasoning | HellaSwag | 31 | Feb 26, 2026 | ||
| IoT/IoMT Attack Detection | CICIoT 2023 (test) | 31 | Feb 26, 2026 | ||
| Reasoning Token Induction | Mixed Prompts (SimpleQA, SimpleBench, AIME2024, etc.) (test) | 31 | Feb 26, 2026 | ||
| Retrieval | HotpotQA (test) | 31 | Jun 30, 2026 | ||
| Language Understanding | MMLU | 31 | Feb 26, 2026 | ||
| Language Modeling | Language Modeling Dataset | 31 | Jul 2, 2026 | ||
| Audio Understanding | MMAU (test) | 31 | Jun 8, 2026 | ||
| Calibration | SQuAD | 31 | Feb 26, 2026 | ||
| Calibration | WebQ | 31 | Feb 26, 2026 | ||
| OS Task | Lifelong Agent Bench OS Task | 31 | Jun 17, 2026 | ||
| LLM-as-a-Judge | RewardBench | 31 | Apr 23, 2026 | ||
| Knowledge | ARC Easy | 31 | Feb 27, 2026 | ||
| Knowledge | ARC Challenge | 31 | Feb 27, 2026 | ||
| Symbolic Reasoning | Last Letter | 31 | May 14, 2026 | ||
| Salience detection | Wikipedia narratives | 31 | Feb 26, 2026 | ||
| Output Diversity | NOVELTYBENCH | 31 | May 29, 2026 | ||
| Medical calculation | MedCalc-Bench | 31 | Jul 3, 2026 | ||
| Hallucination detection | MMLU-Pro | 31 | Jun 23, 2026 | ||
| Tool Use | MCPMark | 31 | Jul 2, 2026 | ||
| Reading Comprehension | BELEBELE | 31 | Feb 26, 2026 |