Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1546 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hospitalization prediction | MIMIC ED IV | 20 | Jun 4, 2026 | ||
| Missing Value Imputation | Bayesian Network MNAR (test) | 20 | Jun 4, 2026 | ||
| Missing Value Imputation | Bayesian Network MAR (test) | 20 | Jun 4, 2026 | ||
| Missing Value Imputation | Bayesian Network MCAR (test) | 20 | Jun 4, 2026 | ||
| Issues-in-dispute ranking | LexIssue (out-of-domain) | 20 | Jun 4, 2026 | ||
| Issues-in-dispute ranking | LexIssue (in-domain) | 20 | Jun 4, 2026 | ||
| Clustering | HandWritten V=6, K=10 (Protocol 2) | 20 | Jun 4, 2026 | ||
| Speech Translation | MCIF long track | 20 | Jun 4, 2026 | ||
| Automatic Speech Recognition | MCIF long track | 20 | Jun 4, 2026 | ||
| Spoken Summarization | MCIF long track | 20 | Jun 4, 2026 | ||
| Spoken Question Answering | MCIF long track | 20 | Jun 4, 2026 | ||
| Dynamic Link Prediction | UN Vote Inductive | 20 | Jun 4, 2026 | ||
| Dynamic Link Prediction | Social Evo. Continuous-time (Inductive) | 20 | Jun 4, 2026 | ||
| Prefill throughput | NOSA-8B | 20 | Jun 4, 2026 | ||
| Prefill throughput | MiniCPM 4.1-8B | 20 | Jun 4, 2026 | ||
| Evidence Localization | Localized-Context synthetic | 20 | Jun 4, 2026 | ||
| General language understanding and reasoning | Open LLM Leaderboard v1 (test) | 20 | Jun 4, 2026 | ||
| Long-context understanding | LongBench v2 (test) | 20 | Jun 4, 2026 | ||
| Capacitated Vehicle Routing Problem (CVRP) | Synthetic CVRP5K | 20 | Jun 4, 2026 | ||
| Capacitated Vehicle Routing Problem (CVRP) | Synthetic CVRP1K | 20 | Jun 4, 2026 | ||
| Star Discrepancy Computation | sequences (test) | 20 | Jun 4, 2026 | ||
| Star Discrepancy Approximation | DGW sequences 10 | 20 | Jun 4, 2026 | ||
| Multi-objective Optimization | DTLZ1 | 20 | Jun 4, 2026 | ||
| Gaussian curvature estimation | Regular vertex | 20 | Jun 4, 2026 | ||
| Reasoning | GPQA Diamond | 20 | Jun 4, 2026 |