Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1923 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Personalized Generation | BESPOKE | 18 | Feb 26, 2026 | ||
| Multi-turn tool use | Xbench | 18 | Feb 26, 2026 | ||
| Multi-turn tool use | BrowseComp-ZH | 18 | Feb 26, 2026 | ||
| Multi-turn tool use | BrowseComp | 18 | Feb 26, 2026 | ||
| Multi-turn tool use | GAIA | 18 | Feb 26, 2026 | ||
| AI Peer Review | PaperAudit-Dataset ICML branch | 18 | Feb 26, 2026 | ||
| GUI Agent Navigation and Action | AITZ | 18 | Mar 24, 2026 | ||
| Tool Use | Tool-use domain Aggregate | 18 | Feb 26, 2026 | ||
| Tool Use | Tool-use domain Subset 3 | 18 | Feb 26, 2026 | ||
| Tool Use | Tool-use domain Subset 2 | 18 | Feb 26, 2026 | ||
| Tool Use | Tool-use domain Subset 1 | 18 | Feb 26, 2026 | ||
| Tool Use | Tool-use domain Subset 0 | 18 | Feb 26, 2026 | ||
| Evidence Grounding | Biomedical QA (test) | 18 | Feb 26, 2026 | ||
| Language model evaluation across subsets | ELEPHANT | 18 | Feb 26, 2026 | ||
| Safety evaluation | SAGE-Eval | 18 | Feb 26, 2026 | ||
| Presupposition correction | Cancer-Myth | 18 | Feb 26, 2026 | ||
| Retrieval | MMEB v2 | 18 | Feb 26, 2026 | ||
| Scientific Coding | SciCode | 18 | Jun 23, 2026 | ||
| Long-term dialogue memory | LongMemEval (test) | 18 | Mar 5, 2026 | ||
| General Knowledge | Knowledge Benchmarks (ARC-C, ARC-E, MMLU, GPQA) (test) | 18 | Feb 27, 2026 | ||
| Safety | HarmBench, SafeChain Safety-Tuned | 18 | Feb 27, 2026 | ||
| View-change prediction | View-change prediction dataset | 18 | Feb 26, 2026 | ||
| Medical Diagnosis | MedEinst Robust 1.0 | 18 | Feb 26, 2026 | ||
| Medical Diagnosis | MedEinst Baseline 1.0 | 18 | Feb 26, 2026 | ||
| Fact-checking | InFi-Check-FG 1.0 (test) | 18 | Feb 26, 2026 |