Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2387 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | KSAT 2025 | 15 | May 26, 2026 | ||
| Textual understanding | SedarEval | 15 | May 26, 2026 | ||
| Textual understanding | IFEval | 15 | May 26, 2026 | ||
| Instruction Following | IFEval | 15 | May 26, 2026 | ||
| Code Generation | HumanEval | 15 | May 26, 2026 | ||
| Mathematical Reasoning | TheoremQA | 15 | May 26, 2026 | ||
| Entity Prediction | WD50K | 15 | May 26, 2026 | ||
| Pairwise Perceived Cycling Safety Modeling | PCS Berlin (test) | 15 | May 26, 2026 | ||
| Subjective evaluation of research ideas | 100 Research Ideas 10 Benchmark Topics | 15 | May 26, 2026 | ||
| Research Idea Generation | Ten benchmark topics (100 generated research ideas) | 15 | May 26, 2026 | ||
| Cyber-Threat Intelligence Mitigation | LLM-CTI Mitigation | 15 | May 26, 2026 | ||
| Cyber-Threat Intelligence Prediction | LLM-CTI (Prediction) | 15 | May 26, 2026 | ||
| Cyber-Threat Intelligence Attribution | LLM-CTI Attribution | 15 | May 26, 2026 | ||
| Cyber-Threat Intelligence Contextualization | LLM-CTI Contextualization | 15 | May 26, 2026 | ||
| Incident Ticket Generation | CTI Benchmark | 15 | May 26, 2026 | ||
| Countermeasure Ranking | CTI Benchmark | 15 | May 26, 2026 | ||
| Defensive Playbook Gen | CTI Benchmark | 15 | May 26, 2026 | ||
| Mitigation–TTP Mapping | CTI Benchmark | 15 | May 26, 2026 | ||
| Response Summarization | CTI Benchmark | 15 | May 26, 2026 | ||
| Rule Generation (YARA) | CTI Benchmark | 15 | May 26, 2026 | ||
| Patch Recommendation | CTI Benchmark | 15 | May 26, 2026 | ||
| Campaign Escalation | CTI Benchmark | 15 | May 26, 2026 | ||
| Target Sector Prediction | CTI Benchmark | 15 | May 26, 2026 | ||
| Impact Forecast | CTI Benchmark | 15 | May 26, 2026 | ||
| Exploit Likelihood | CTI Benchmark | 15 | May 26, 2026 |