Loading model details...
Claude Sonnet 4.5 | DAXBench
Back to Leaderboard
Anthropic
Claude Sonnet 4.5
Rank
#34
Overview
Analytics
Score Overview
77.9%
Overall Score
76.7%
Accuracy
100.0%
Syntax Valid
Score Dimensions
81
Correctness
86
Best Practices
86
Performance
85
Clarity
Performance by Complexity
Basic
100.0%
Intermediate
85.8%
Advanced
62.8%
Tasks Correct
23 / 30
Avg Response Time
2087ms
Task Breakdown
Summary
Dimensions
Task
Category
Score
Time
Total Sales Amount
task-001
aggregation
100%
2040ms
Count of Customers
task-002
aggregation
100%
1552ms
Average Unit Price
task-003
aggregation
100%
1758ms
Distinct Product Count
task-004
aggregation
100%
1694ms
Total Order Quantity
task-005
aggregation
100%
1608ms
Year-to-Date Sales
task-006
time intelligence
100%
2048ms
Previous Year Sales
task-007
time intelligence
100%
2036ms
Sales by Category Filter
task-008
filtering
100%
1871ms
Year-over-Year Growth Percentage
task-009
calculation
30%
2724ms
Running Total with CALCULATE and FILTER
Query Failed
task-010
iterator
10%
2253ms
Sales Summary by Category
task-011
table manipulation
100%
1992ms
Product List with Renamed Columns
task-012
table manipulation
100%
1980ms
Union of High-Value Transactions
task-013
table manipulation
30%
2607ms
Year-Category Analysis Matrix
Query Failed
task-014
table manipulation
10%
1849ms
Product Percentage of Category Total
task-015
context transition
100%
2603ms
Virtual Relationship with TREATAS
task-016
context transition
100%
2423ms
Granularity-Aware Measure with VALUES
task-017
context transition
100%
2438ms
Running Count with EARLIER
task-018
context transition
30%
1989ms
Multiple Filter Conditions
task-019
filtering
100%
1512ms
Percentage of Total with ALLEXCEPT
task-020
filtering
100%
2302ms
Filter Intersection with KEEPFILTERS
task-021
filtering
100%
1659ms
Product Ranking with RANKX
Query Failed
task-022
iterator
10%
2376ms
Top 5 Products with TOPN
task-023
table manipulation
100%
2349ms
90th Percentile Order Value
task-024
iterator
100%
1642ms
Handle Missing Data with BLANK
task-025
calculation
100%
1633ms
Safe Ratio with Cascading Fallbacks
task-026
calculation
100%
2686ms
Safe Year-over-Year with Missing Data
task-027
time intelligence
100%
3027ms
3-Month Rolling Average
task-028
time intelligence
100%
2498ms
Same Month Previous Year Comparison
Query Failed
task-029
time intelligence
10%
1577ms
Fiscal Year-to-Date (July Start)
task-030
time intelligence
100%
1893ms