| Rank | Dataset | Year | Size | Avg Score | Efficiency | General | Math | Code | Reasoning |
|---|---|---|---|---|---|---|---|---|---|
|
{{ getRank(dataset, filteredDataForRanking, (sortColumn === 'year' || sortColumn === 'name' || sortColumn === 'size') ? 'overall_avg' : sortColumn, false, null, improvementType) }}
{{ dataset.domain === 'base' ? 'Currently using Base Model as comparison baseline' : 'Currently using Instruct Model as comparison baseline' }}
|
{{ dataset.affiliation }}
|
{{ dataset.domain === 'base' || dataset.domain === 'instruct' ? '-' : dataset.year }} | {{ dataset.domain === 'base' || dataset.domain === 'instruct' ? '-' : dataset.size }} |
{{ formatScoreWithImprovement(dataset.overall_avg, dataset.improvement?.overall_avg, dataset, improvementType).score }}
{{ formatScoreWithImprovement(dataset.overall_avg, dataset.improvement?.overall_avg, dataset, improvementType).diffText }}
|
{{ formatEfficiencyScore(dataset.overall_efficiency) }}
|
{{ formatScoreWithImprovement(dataset.general_avg, dataset.improvement?.general_avg, dataset, improvementType).score }}
{{ formatScoreWithImprovement(dataset.general_avg, dataset.improvement?.general_avg, dataset, improvementType).diffText }}
|
{{ formatScoreWithImprovement(dataset.math_avg, dataset.improvement?.math_avg, dataset, improvementType).score }}
{{ formatScoreWithImprovement(dataset.math_avg, dataset.improvement?.math_avg, dataset, improvementType).diffText }}
|
{{ formatScoreWithImprovement(dataset.code_avg, dataset.improvement?.code_avg, dataset, improvementType).score }}
{{ formatScoreWithImprovement(dataset.code_avg, dataset.improvement?.code_avg, dataset, improvementType).diffText }}
|
{{ formatScoreWithImprovement(dataset.reasoning_avg, dataset.improvement?.reasoning_avg, dataset, improvementType).score }}
{{ formatScoreWithImprovement(dataset.reasoning_avg, dataset.improvement?.reasoning_avg, dataset, improvementType).diffText }}
|
{{ getTypeDisplayName(selectedType) }} Leaderboard
| Rank | Dataset | Year | Size | Avg Score | Efficiency |
{{ header.displayName }}
{{ header.metricDisplayName }}
|
|---|---|---|---|---|---|---|
|
{{ getRank(dataset, detailedFilteredDataForRanking, (detailedSortColumn === 'year' || detailedSortColumn === 'name' || detailedSortColumn === 'size') ? 'average' : (detailedSortColumn || 'average'), true, selectedType, improvementType) }}
{{ dataset.domain === 'base' ? 'Currently using Base Model as comparison baseline' : 'Currently using Instruct Model as comparison baseline' }}
|
{{ dataset.affiliation }}
|
{{ dataset.domain === 'base' || dataset.domain === 'instruct' ? '-' : dataset.year }} | {{ dataset.domain === 'base' || dataset.domain === 'instruct' ? '-' : dataset.size }} |
{{ getTypeAverage(dataset, selectedType, improvementType).score }}
{{ getTypeAverage(dataset, selectedType, improvementType).diffText }}
|
{{ formatEfficiencyScore(getTypeEfficiency(dataset, selectedType)) }}
|
{{ getTaskScore(dataset, selectedType, header.taskName, header.metricName, false, improvementType).score }}
{{ getTaskScore(dataset, selectedType, header.taskName, header.metricName, false, improvementType).diffText }}
|