ResearchTasksCost-aware LLM RoutingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOllama-cloud trio 300 unique tasks x 3 repeats (hard-benchmark)Oracle (per-task max)91.2Quality Score (q)7May 12, 2026
Ollama-cloud trio 300 unique tasks x 3 repeats (hard-benchmark)Oracle (per-task max)91.2Quality Score (q)7May 12, 2026