Back to Dashboard
CategoryWeight: 1.0x

Performance Efficiency

Tests whether generated code uses efficient algorithms and avoids unnecessary computation, memory allocation, and I/O.

Best Score

0.0

Avg Score

0.0

Tests

3

Performance Over Time — All Models

Model Rankings

1
Claude Opus 5

Category score

View
92.7BEST
Tokens51.3k
Total51.3k
2
Claude Sonnet 5

Category score

View
92.3-0.4 pts
Tokens28.3k
Total28.3k
3
GPT-5.6 Sol

Category score

View
92.0-0.7 pts
Tokens51.5k
Total51.5k
4
Grok 4.5

Category score

View
90.0-2.7 pts
Tokens95.8k
Total95.8k

Test Breakdown

Algorithm Complexity

Solve a problem in O(n log n) instead of naive O(n^2)

Claude Opus 5
97.0
Claude Sonnet 5
98.0
GPT-5.6 Sol
97.0
Grok 4.5
98.0

Memory-efficient Processing

Process a large file using streaming instead of loading into memory

Claude Opus 5
91.0
Claude Sonnet 5
88.0
GPT-5.6 Sol
91.0
Grok 4.5
84.0

Query Optimization

Write database queries that use indexes and avoid N+1 patterns

Claude Opus 5
90.0
Claude Sonnet 5
91.0
GPT-5.6 Sol
88.0
Grok 4.5
88.0