Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 289 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Malware Classification | CICMalDroid 2020 | 60 | Jun 8, 2026 | ||
| Malicious Tool Detection | Dataset II Trojan malicious tools 1.0 (test) | 60 | Feb 26, 2026 | ||
| Mathematics | AIME 2024 | 60 | Apr 3, 2026 | ||
| Logical Reasoning | AR-LSAT | 60 | Apr 20, 2026 | ||
| Speech Reconstruction | LibriSpeech clean (test) | 60 | Jun 30, 2026 | ||
| Science Question Answering | ARC Challenge (test) | 60 | Jul 3, 2026 | ||
| LLM Calibration | MACE | 60 | Feb 26, 2026 | ||
| Math Reasoning | MATH 500 | 60 | Apr 8, 2026 | ||
| Reasoning | Sudoku | 60 | Jun 4, 2026 | ||
| Text-based safety moderation | BeaverTails | 60 | Jun 23, 2026 | ||
| Single-hop Question Answering | TriviaQA (test) | 60 | Jul 7, 2026 | ||
| Optimization Modeling | OptMATH | 60 | Jun 16, 2026 | ||
| Audio-visual understanding | Daily-Omni | 60 | Jun 23, 2026 | ||
| Symbolic Regression | 3D Advection Equation (test) | 60 | Feb 26, 2026 | ||
| Conformal Inference | Average across 15 datasets (test) | 60 | Feb 26, 2026 | ||
| Sentiment Extraction | TweetSentimentExtraction | 60 | Feb 26, 2026 | ||
| Faithfulness Hallucination | FollowRAG Faithfulness+ | 60 | Feb 26, 2026 | ||
| Fingerprint Verification | Fingerprint Verification | 60 | Feb 26, 2026 | ||
| Fingerprint Verification | Shisa-7B and Abel-7B-002 Merged | 60 | Feb 26, 2026 | ||
| Japanese Language Understanding | JAQKET | 60 | Feb 26, 2026 | ||
| Fingerprint Verification | Embedded Fingerprints (test) | 60 | Feb 26, 2026 | ||
| Safety Evaluation | LLaMA-2-7B-CHAT Safety (test) | 60 | Feb 26, 2026 | ||
| Mathematical Reasoning | WizardMath (test) | 60 | Feb 26, 2026 | ||
| Click-Through Rate Prediction | Avazu | 60 | May 26, 2026 | ||
| Question Answering | ARC-e (test) | 60 | Jun 30, 2026 |