Benchmark results for LLM performance on Nonogram puzzle solving. Comparing accuracy, speed, and cost across different grid sizes.
Last updated: 12/29/2025, 4:45:26 PM
Avg Accuracy
20.0%
Solved
6/30
Avg Time
39.75s
Total Cost
$0.24
Avg Accuracy
10.0%
Solved
3/30
Avg Time
129.14s
Total Cost
$1.98
Avg Accuracy
3.3%
Solved
1/30
Avg Time
151.17s
Total Cost
$1.95
Running benchmarks isn't cheap. If you find this useful and want to support the project, consider buying me a coffee.